1
|
Tari SY, Heikal A, Le C, Yang F, Dinakaran D, Amanie J, Murtha A, Rowe LS, Roa WH, Patel S. Left hippocampus sparing model for glioblastoma radiotherapy by utilizing knowledge-based planning and multi-criteria optimization. J Appl Clin Med Phys 2025:e70014. [PMID: 39955265 DOI: 10.1002/acm2.70014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2024] [Revised: 09/21/2024] [Accepted: 12/03/2024] [Indexed: 02/17/2025] Open
Abstract
PURPOSE Results of a prospective, randomized controlled trial at our institute demonstrate an association between the dose to the left hippocampus and neurocognitive decline post-radiotherapy for patients with glioblastoma. To minimize the dose to the left hippocampus, a left hippocampus sparing model was created using RapidPlan (RP) and multi-criteria optimization (MCO). MATERIALS AND METHODS For 147 patients with newly diagnosed glioblastoma treated with volumetric modulated arc therapy (VMAT), the left and right hippocampus were delineated. Ninety-seven of 147 VMAT plans were used to configure a RP model named HCS1. The remaining 50 VMAT plans were used for the model validation. All 97 plans were replanned with the HCS1 and further optimized using MCO (HCS1+MCO). MCO was used to explore the trade-off between reducing the left hippocampus mean dose and planning objectives for the targets and other organs-at-risk (OAR) for HCS1 plans. These plans were used to create a new model called HCS2. MCO and RP model configuration were done within the Eclipse treatment planning system. RESULTS The final HCS2 model decreased the mean dose to the left hippocampus by 26% compared to clinically treated plans without reducing target coverage for 50 validation data. The mean dose to the left hippocampus decreased from 32.65 Gy in clinically treated plans, 30.45 Gy in HCS1-generated plans, and 24.04 Gy in HCS2-generated plans. The mean volume receiving 95% of the prescription dose (V95%) of the planning target volume was 99.08% ± 1.39% in clinically treated plans, 99.03% ± 1.37% in HCS1-generated plans, and 98.80% ± 1.48% in HCS2-generated plans. Mean dose to 0.1 cc of the brainstem improved from 45.91 Gy in clinically treated plans to 39.29 Gy in HCS2-generated plans. CONCLUSIONS The RP model and MCO helps to decrease left hippocampus mean dose while maintaining the target volume coverage and OAR sparing comparable to clinically treated plans for glioblastoma patients.
Collapse
Affiliation(s)
- Shima Y Tari
- Department of Medical Physics, Cross Cancer Institute, Edmonton, Alberta, Canada
- Department of Oncology, Division of Medical Physics, University of Alberta, Edmonton, Alberta, Canada
| | - Amr Heikal
- Department of Medical Physics, Cross Cancer Institute, Edmonton, Alberta, Canada
- Department of Oncology, Division of Medical Physics, University of Alberta, Edmonton, Alberta, Canada
| | - Connie Le
- Division of Radiation Oncology, Department of Oncology, University of Alberta, Edmonton, Alberta, Canada
| | - Fan Yang
- Division of Radiation Oncology, Department of Oncology, University of Alberta, Edmonton, Alberta, Canada
| | - Deepak Dinakaran
- Division of Radiation Oncology, Department of Oncology, University of Alberta, Edmonton, Alberta, Canada
| | - John Amanie
- Division of Radiation Oncology, Department of Oncology, University of Alberta, Edmonton, Alberta, Canada
| | - Albert Murtha
- Division of Radiation Oncology, Department of Oncology, University of Alberta, Edmonton, Alberta, Canada
| | - Lindsay S Rowe
- Division of Radiation Oncology, Department of Oncology, University of Alberta, Edmonton, Alberta, Canada
| | - Wilson H Roa
- Division of Radiation Oncology, Department of Oncology, University of Alberta, Edmonton, Alberta, Canada
| | - Samir Patel
- Division of Radiation Oncology, Department of Oncology, University of Alberta, Edmonton, Alberta, Canada
| |
Collapse
|
2
|
Hou X, Cheng W, Shen J, Guan H, Zhang Y, Bai L, Wang S, Liu Z. A deep learning model to predict dose distributions for breast cancer radiotherapy. Discov Oncol 2025; 16:165. [PMID: 39937302 PMCID: PMC11822156 DOI: 10.1007/s12672-025-01942-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/03/2024] [Accepted: 02/05/2025] [Indexed: 02/13/2025] Open
Abstract
PURPOSE In this work, we propose to develop a 3D U-Net-based deep learning model that accurately predicts the dose distribution for breast cancer radiotherapy. METHODS This study included 176 breast cancer patients, divided into training, validating and testing sets. A deep learning model based on the 3D U-Net architecture was developed to predict dose distribution, which employed a double encoder combination attention (DECA) module, a cross stage partial + Resnet + Attention (CRA) module, a difficulty perception and a critical regions loss. The performance and generalization ability of this model were evaluated by the voxel mean absolute error (MAE), several clinically relevant dosimetric indexes and 3D gamma passing rates. RESULTS Our model accurately predicted the 3D dose distributions with each dosage level mirroring the clinical reality in shape. The generated dose-volume histogram (DVH) matched with the ground truth curve. The total dose error of our model was below 1.16 Gy, complying with clinical usage standards. When compared to other exceptional models, our model optimally predicted eight out of nine regions, and the prediction errors for the first planning target volume (PTV1) and PTV2 were merely 1.03 Gy and 0.74 Gy. Moreover, the mean 3%/3 mm 3D gamma passing rates for PTV1, PTV2, Heart and Lung L achieved 91.8%, 96.4%, 91.5%, and 93.2%, respectively, surpassing the other models and meeting clinical standards. CONCLUSIONS This study developed a new deep learning model based on 3D U-Net that can accurately predict dose distributions for breast cancer radiotherapy, which can improve the quality and planning efficiency.
Collapse
Affiliation(s)
- Xiaorong Hou
- Department of Radiation Oncology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China
| | - Weishi Cheng
- Department of Radiation Oncology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, 100730, China
| | - Jing Shen
- Department of Radiation Oncology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China
| | - Hui Guan
- Department of Radiation Oncology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China
| | - Yimeng Zhang
- MedMind Technology Co. Ltd., AB 1920 Techart Plaza, Beijing, 100083, China
| | - Lu Bai
- MedMind Technology Co. Ltd., AB 1920 Techart Plaza, Beijing, 100083, China
| | - Shaobin Wang
- MedMind Technology Co. Ltd., AB 1920 Techart Plaza, Beijing, 100083, China
| | - Zhikai Liu
- Department of Radiation Oncology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China.
| |
Collapse
|
3
|
Chen X, Shi X, Zhang H, Pang H. Quality control study of cervical cancer interstitial brachytherapy treatment plans using statistical process control. Brachytherapy 2025:S1538-4721(25)00005-4. [PMID: 39893114 DOI: 10.1016/j.brachy.2024.12.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2024] [Revised: 11/18/2024] [Accepted: 12/30/2024] [Indexed: 02/04/2025]
Abstract
OBJECTIVE This study explored using statistical process control for quality control of cervical cancer interstitial brachytherapy treatment plans. MATERIALS AND METHODS For retrospective analysis, interstitial brachytherapy treatment plans were divided into first (n = 300) and second phases (n = 200). The first phase was chronologically divided 2:1 into training and validation sets. The Dn2cm3 (D2cm3 divided by the high-risk clinical target volume D90) of the organs at risk (the bladder, rectum, and sigmoid colon) were analyzed to draw individual control charts. Process capability analysis charts were drawn, and the statistical process capability was evaluated using the process capability index Cpk. The centerline of the organ at risk dose in the first-phase plan's training set was used as the optimization parameter for the second-phase dataset plan. RESULTS The Dn2cm3 centerlines for the bladder, rectum, and sigmoid colon were 0.6980, 0.5440, and 0.4910 in the training set and 0.6845, 0.4528, and 0.4144 in the second phase, respectively. The first-phase δ values were 0.0099, 0.0530, and 0.0268, respectively. The process capability analysis for the first and second phases showed that all indicators had a Cpk >1. CONCLUSION For all organs at risk, the Dn2cm3 centerlines were lower in the second phase than in the first phase, indicating that quality control of cervical cancer interstitial brachytherapy treatment plans continuously improved through statistical process control. This method is simple and practical and warrants promotion for application in radiotherapy treatment plan quality control.
Collapse
Affiliation(s)
- Xiao Chen
- Department of Oncology, The Affiliated Hospital of Southwest Medical University, Sichuan, China
| | - Xiangxiang Shi
- Department of Oncology, The Affiliated Hospital of Southwest Medical University, Sichuan, China
| | - Huaiwen Zhang
- Department of Radiotherapy, Jiangxi Cancer Hospital, The Second Affiliated Hospital of Nanchang Medical College, Jiangxi Clinical Research Center for Cancer, Nanchang, China
| | - Haowen Pang
- Department of Oncology, The Affiliated Hospital of Southwest Medical University, Sichuan, China.
| |
Collapse
|
4
|
Liu X, Chen D, Liu Y, Men K, Dai J, Quan H, Chen X. Cross-technique transfer learning for autoplanning in magnetic resonance imaging-guided adaptive radiotherapy for rectal cancer. Phys Med 2025; 129:104873. [PMID: 39709892 DOI: 10.1016/j.ejmp.2024.104873] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/25/2024] [Revised: 10/09/2024] [Accepted: 11/30/2024] [Indexed: 12/24/2024] Open
Abstract
PURPOSE Automated treatment plan generation is essential for magnetic resonance imaging (MRI)-guided adaptive radiotherapy (MRIgART) to ensure standardized treatment-plan quality. We proposed a novel cross-technique transfer learning (CTTL)-based strategy for online MRIgART autoplanning. METHOD We retrospectively analyzed the data from 210 rectal cancer patients. A source dose prediction model was initially trained using a large volume of volumetric-modulated arc therapy data. Subsequently, a single patient's pretreatment data was employed to construct a CTTL-based dose prediction model (CTTL_M) for each new patient undergoing MRIgART. The CTTL_M predicted dose distributions for subsequent treatment fractions. We optimized an auto plan using the parameters based on dose prediction. Performance of our CTTL_M was assessed using dose-volume histogram and mean absolute error (MAE). Our auto plans were compared with clinical plans regarding plan quality, efficiency, and complexity. RESULTS CTTL_M significantly improved the dose prediction accuracy, particularly in planning target volumes (median MAE: 1.27 % vs. 7.06 %). The auto plans reduced high-dose exposure to the bladder (D0.1cc: 2,601.93 vs. 2,635.43 cGy, P < 0.001) and colon (D0.1cc: 2,593.22 vs. 2,624.89 cGy, P < 0.001). The mean colon dose decreased from 1,865.08 to 1,808.16 cGy (P = 0.035). The auto plans maintained similar planning time, monitor units, and plan complexity as clinical plans. CONCLUSIONS We proposed an online ART autoplanning method for generating high-quality plans with improved organ sparing. Its high degree of automation can standardize planning quality across varying expertise levels, mitigating subjective assessment and errors.
Collapse
Affiliation(s)
- Xiaonan Liu
- School of Physics and Technology, Wuhan University, Wuhan 430072, China; National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| | - Deqi Chen
- National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| | - Yuxiang Liu
- National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| | - Kuo Men
- National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| | - Jianrong Dai
- National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
| | - Hong Quan
- School of Physics and Technology, Wuhan University, Wuhan 430072, China.
| | - Xinyuan Chen
- National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China.
| |
Collapse
|
5
|
Li X, Sheng Y, Wu QJ, Ge Y, Brizel DM, Mowery YM, Yang D, Yin F, Wu Q. Clinical commissioning and introduction of an in-house artificial intelligence (AI) platform for automated head and neck intensity modulated radiation therapy (IMRT) treatment planning. J Appl Clin Med Phys 2025; 26:e14558. [PMID: 39503512 PMCID: PMC11712748 DOI: 10.1002/acm2.14558] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2024] [Revised: 07/30/2024] [Accepted: 09/25/2024] [Indexed: 11/08/2024] Open
Abstract
BACKGROUND AND PURPOSE To describe the clinical commissioning of an in-house artificial intelligence (AI) treatment planning platform for head-and-neck (HN) Intensity Modulated Radiation Therapy (IMRT). MATERIALS AND METHODS The AI planning platform has three components: (1) a graphical user interface (GUI) is built within the framework of a commercial treatment planning system (TPS). The GUI allows AI models to run remotely on a designated workstation configured with GPU acceleration. (2) A template plan is automatically prepared involving both clinical and AI considerations, which include contour evaluation, isocenter placement, and beam/collimator jaw placement. (3) A well-orchestrated suite of AI models predicts optimal fluence maps, which are imported into TPS for dose calculation followed by an optional automatic fine-tuning. Six AI models provide flexible tradeoffs in parotid sparing and Planning Target Volume (PTV)-organ-at-risk (OAR) preferences. Planners could examine the plan dose distribution and make further modifications as clinically needed. The performance of the AI plans was compared to the corresponding clinical plans. RESULTS The average plan generation time including manual operations was 10-15 min per case, with each AI model prediction taking ∼1 s. The six AI plans form a wide range of tradeoff choices between left and right parotids and between PTV and OARs compared with corresponding clinical plans, which correctly reflected their tradeoff designs. CONCLUSION The in-house AI IMRT treatment planning platform was developed and is available for clinical use at our institution. The process demonstrates outstanding performance and robustness of the AI platform and provides sufficient validation.
Collapse
Affiliation(s)
- Xinyi Li
- Department of Radiation OncologyDuke University Medical CenterDurhamNorth CarolinaUnited States
| | - Yang Sheng
- Department of Radiation OncologyDuke University Medical CenterDurhamNorth CarolinaUnited States
| | - Qingrong Jackie Wu
- Department of Radiation OncologyDuke University Medical CenterDurhamNorth CarolinaUnited States
| | - Yaorong Ge
- Department of Information SystemsUniversity of North Carolina at CharlotteCharlotteNorth CarolinaUnited States
| | - David M. Brizel
- Department of Radiation OncologyDuke University Medical CenterDurhamNorth CarolinaUnited States
- Department of Head and Neck Surgery and Communication SciencesDuke University Medical CenterDurhamNorth CarolinaUnited States
| | - Yvonne M. Mowery
- Department of Radiation OncologyDuke University Medical CenterDurhamNorth CarolinaUnited States
| | - Dongrong Yang
- Department of Radiation OncologyDuke University Medical CenterDurhamNorth CarolinaUnited States
| | - Fang‐Fang Yin
- Department of Radiation OncologyDuke University Medical CenterDurhamNorth CarolinaUnited States
| | - Qiuwen Wu
- Department of Radiation OncologyDuke University Medical CenterDurhamNorth CarolinaUnited States
| |
Collapse
|
6
|
Landoni V, Broggi S, Serra M, Doro R, Stefania Martinotti A, Redaelli I, Cristina Frassanito M, Siragusa C, De Martin E, Soriani A, Tudda A, Castriconi R, Del Vecchio A, Masi L, Fiorino C. Multicenter approach to predict plan quality of robotic intracranial SRS/SRT. Phys Med 2025; 129:104887. [PMID: 39742827 DOI: 10.1016/j.ejmp.2024.104887] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/27/2024] [Revised: 11/13/2024] [Accepted: 12/27/2024] [Indexed: 01/04/2025] Open
Abstract
PURPOSE This study analyzed inter-institute conformity and dose gradient variability of CyberKnife (CK) brain SRS/SRT plans. The feasibility of multi-center predictive models was investigated, aiming at guided/automated planning optimization. METHODS Data from 335 clinical plans, delivered for single lesions in 1-5 fractions, were collected by 8 CK centers. Conformity index (CI), Dose Gradient Index (DGI) and the effective radii defined by different isodose volumes (Reff) were computed. Predictability of dose fall-off from PTV dimensions was analyzed. DGI average, 80th and 10thpercentile values were evaluated stratifying plans by PTV size into six groups. Linear regression models were created for Reff as a function of PTV equivalent radius. RESULTS CI values (range 0.96---2.23) exceeded 1.20 in 88/335 plans, mostly (65 %) collected in 2 of the participating centers. DGI showed an acceptable inter-institute variability and a strong significant correlation (p < 0.0001) with PTV. Ideal and Minimal DGI for each of the six groups were respectively 95 (86), 82 (73), 77 (68), 71 (60), 59 (43) and 50 (29). The rate of DGI values passing the multicenter minimal criteria, considering each center separately, varied from 43 % to 100 %. R2values for the regression between Reff and PTV radius were ≥ 0.958, showing an increasing inter-center variability for decreasing isodose values. CONCLUSION Observed inter-center differences enhanced the advantages of a multi-institute approach. Multicenter predictive models for dose fall-off in CK brain SR/SRT planning are feasible and easy to use. Reff models and DGI analysis may permit to partially automate planning optimization avoiding creation of suboptimal plans.
Collapse
Affiliation(s)
- Valeria Landoni
- Medical Physics Department, IRCCS Regina Elena National Cancer Institute, Rome, Italy; Medical Physics Unit. A.O. San Camillo Forlanini, Rome, Italy.
| | - Sara Broggi
- IRCCS San Raffaele Scientific Institute, Medical Physics, Milano, Italy
| | - Marcello Serra
- Department of Radiation Oncology, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131 Napoli, Italy
| | - Raffaella Doro
- Department of Radiation Oncology, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131 Napoli, Italy; Department of Medical Physics and Radiation Oncology, IFCA, Florence, Italy
| | | | - Irene Redaelli
- Cyberknife Department, Centro Diagnostico Italiano, I-20147 Milano, Italy
| | | | - Carmelo Siragusa
- Medical Physics Unit, A.O.U. Policlinico G. Martino, Messina, Italy
| | - Elena De Martin
- Health Department, Fondazione IRCCS Istituto Neurologico Carlo Besta, 20133 Milan, Italy
| | - Antonella Soriani
- Medical Physics Department, IRCCS Regina Elena National Cancer Institute, Rome, Italy
| | - Alessia Tudda
- IRCCS San Raffaele Scientific Institute, Medical Physics, Milano, Italy
| | | | | | - Laura Masi
- Department of Medical Physics and Radiation Oncology, IFCA, Florence, Italy
| | - Claudio Fiorino
- IRCCS San Raffaele Scientific Institute, Medical Physics, Milano, Italy
| |
Collapse
|
7
|
Liu M, Pang B, Chen S, Zeng Y, Zhang Q, Quan H, Chang Y, Yang Z. Deep learning-based multiple-CT optimization: An adaptive treatment planning approach to account for anatomical changes in intensity-modulated proton therapy for head and neck cancers. Radiother Oncol 2025; 202:110650. [PMID: 39581351 DOI: 10.1016/j.radonc.2024.110650] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2024] [Revised: 11/15/2024] [Accepted: 11/19/2024] [Indexed: 11/26/2024]
Abstract
BACKGROUNDS Intensity-modulated proton therapy (IMPT) is particularly susceptible to range and setup uncertainties, as well as anatomical changes. PURPOSE We present a framework for IMPT planning that employs a deep learning method for dose prediction based on multiple-CT (MCT). The extra CTs are created from cone-beam CT (CBCT) using deformable registration with the primary planning CT (PCT). Our method also includes a dose mimicking algorithm. METHODS The MCT IMPT planning pipeline involves prediction of robust dose from input images using a deep learning model with a U-net architecture. Deliverable plans may then be created by solving a dose mimicking problem with the predictions as reference dose. Model training, dose prediction and plan generation are performed using a dataset of 55 patients with head and neck cancer in this retrospective study. Among them, 38 patients were used as training set, 7 patients were used as validation set, and 10 patients were reserved as test set for final evaluation. RESULTS We demonstrated that the deliverable plans generated through subsequent MCT dose mimicking exhibited greater robustness than the robust plans produced by the PCT, as well as enhanced dose sparing for organs at risk. MCT plans had lower D2% (76.1 Gy vs. 82.4 Gy), better homogeneity index (7.7% vs. 16.4%) of CTV1 and better conformity index (70.5% vs. 61.5%) of CTV2 than the robust plans produced by the primary planning CT for all test patients. CONCLUSIONS We demonstrated the feasibility and advantages of incorporating daily CBCT images into MCT optimization. This approach improves plan robustness against anatomical changes and may reduce the need for plan adaptations in head and neck cancer treatments.
Collapse
Affiliation(s)
- Muyu Liu
- Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan 430072, China
| | - Bo Pang
- Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan 430072, China
| | - Shuoyan Chen
- Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan 430072, China
| | - Yiling Zeng
- Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan 430072, China
| | - Qi Zhang
- Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan 430072, China
| | - Hong Quan
- Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan 430072, China.
| | - Yu Chang
- Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China; Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China; Hubei Key Laboratory of Precision Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
| | - Zhiyong Yang
- Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China; Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China; Hubei Key Laboratory of Precision Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
| |
Collapse
|
8
|
Conroy L, Winter J, Khalifa A, Tsui G, Berlin A, Purdie TG. Artificial Intelligence for Radiation Treatment Planning: Bridging Gaps From Retrospective Promise to Clinical Reality. Clin Oncol (R Coll Radiol) 2025; 37:103630. [PMID: 39531894 DOI: 10.1016/j.clon.2024.08.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2023] [Revised: 07/31/2024] [Accepted: 08/08/2024] [Indexed: 11/16/2024]
Abstract
Artificial intelligence (AI) radiation therapy (RT) planning holds promise for enhancing the consistency and efficiency of the RT planning process. Despite technical advancements, the widespread integration of AI into RT treatment planning faces challenges. The transition from controlled retrospective environments to real-world clinical settings introduces heightened scrutiny from clinical end users, potentially leading to decreased clinical acceptance. Key considerations for implementing AI RT planning include ensuring the AI model performance aligns with clinical standards, using high-quality training data, and incorporating sufficient data variation through meticulous curation by clinical experts. Beyond technical aspects, factors such as potential biases and the level of trust clinical end users place in AI may present unforeseen obstacles for real-world clinical use. Addressing these challenges requires bridging education and expertise gaps among clinical end users, enabling them to confidently embrace and utilize AI for routine RT planning. By fostering a better understanding of AI capabilities, building trust, and providing comprehensive training, the promises of AI RT planning can be a reality in the clinical setting. This article assesses the current clinical use of AI RT planning and explores challenges and considerations for bridging gaps in knowledge and expertise for AI operationalization, with focus on training data curation, workflow integration, explainability, bias, and domain knowledge. Remaining challenges in clinical implementation of AI RT treatment planning are examined in the context of trust building approaches.
Collapse
Affiliation(s)
- L Conroy
- Radiation Medicine Program, Princess Margaret Cancer Centre, 610 University Avenue, Toronto, Ontario, M5G 2M9, Canada; Techna Insitute, University Health Network, 190 Elizabeth St, Toronto, Ontario, M5G 2C4, Canada; Department of Radiation Oncology, University of Toronto, 149 College Street - Stewart Building Suite 504, Toronto, Ontario, M5T 1P5, Canada.
| | - J Winter
- Radiation Medicine Program, Princess Margaret Cancer Centre, 610 University Avenue, Toronto, Ontario, M5G 2M9, Canada; Techna Insitute, University Health Network, 190 Elizabeth St, Toronto, Ontario, M5G 2C4, Canada; Department of Radiation Oncology, University of Toronto, 149 College Street - Stewart Building Suite 504, Toronto, Ontario, M5T 1P5, Canada.
| | - A Khalifa
- Techna Insitute, University Health Network, 190 Elizabeth St, Toronto, Ontario, M5G 2C4, Canada; Department of Medical Biophysics, University of Toronto, Princess Maragret Cancer Research Tower, MaRS Centre, 101 College Street, Room 15-701, Toronto, Ontario, M5G 1L7, Canada.
| | - G Tsui
- Radiation Medicine Program, Princess Margaret Cancer Centre, 610 University Avenue, Toronto, Ontario, M5G 2M9, Canada.
| | - A Berlin
- Radiation Medicine Program, Princess Margaret Cancer Centre, 610 University Avenue, Toronto, Ontario, M5G 2M9, Canada; Techna Insitute, University Health Network, 190 Elizabeth St, Toronto, Ontario, M5G 2C4, Canada; Department of Radiation Oncology, University of Toronto, 149 College Street - Stewart Building Suite 504, Toronto, Ontario, M5T 1P5, Canada.
| | - T G Purdie
- Radiation Medicine Program, Princess Margaret Cancer Centre, 610 University Avenue, Toronto, Ontario, M5G 2M9, Canada; Techna Insitute, University Health Network, 190 Elizabeth St, Toronto, Ontario, M5G 2C4, Canada; Department of Radiation Oncology, University of Toronto, 149 College Street - Stewart Building Suite 504, Toronto, Ontario, M5T 1P5, Canada; Department of Medical Biophysics, University of Toronto, Princess Maragret Cancer Research Tower, MaRS Centre, 101 College Street, Room 15-701, Toronto, Ontario, M5G 1L7, Canada.
| |
Collapse
|
9
|
Damilakis J, Stratakis J. Descriptive overview of AI applications in x-ray imaging and radiotherapy. JOURNAL OF RADIOLOGICAL PROTECTION : OFFICIAL JOURNAL OF THE SOCIETY FOR RADIOLOGICAL PROTECTION 2024; 44:041001. [PMID: 39681008 DOI: 10.1088/1361-6498/ad9f71] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/21/2024] [Accepted: 12/16/2024] [Indexed: 12/18/2024]
Abstract
Artificial intelligence (AI) is transforming medical radiation applications by handling complex data, learning patterns, and making accurate predictions, leading to improved patient outcomes. This article examines the use of AI in optimising radiation doses for x-ray imaging, improving radiotherapy outcomes, and briefly addresses the benefits, challenges, and limitations of AI integration into clinical workflows. In diagnostic radiology, AI plays a pivotal role in optimising radiation exposure, reducing noise, enhancing image contrast, and lowering radiation doses, especially in high-dose procedures like computed tomography (CT). Deep learning (DL)-powered CT reconstruction methods have already been incorporated into clinical routine. Moreover, AI-powered methodologies have been developed to provide real-time, patient-specific radiation dose estimates. These AI-driven tools have the potential to streamline workflows and potentially become integral parts of imaging practices. In radiotherapy, AI's ability to automate and enhance the precision of treatment planning is emphasised. Traditional methods, such as manual contouring, are time-consuming and prone to variability. AI-driven techniques, particularly DL models, are automating the segmentation of organs and tumours, improving the accuracy of radiation delivery, and minimising damage to healthy tissues. Moreover, AI supports adaptive radiotherapy, allowing continuous optimisation of treatment plans based on changes in a patient's anatomy over time, ensuring the highest accuracy in radiation delivery and better therapeutic outcomes. Some of these methods have been validated and integrated into radiation treatment systems, while others are not yet ready for routine clinical use mainly due to challenges in validation, particularly ensuring reliability across diverse patient populations and clinical settings. Despite the potential of AI, there are challenges in fully integrating these technologies into clinical practice. Issues such as data protection, privacy, data quality, model validation, and the need for large and diverse datasets are crucial to ensuring the reliability of AI systems.
Collapse
Affiliation(s)
- John Damilakis
- School of Medicine, University of Crete, Heraklion, Greece
- University Hospital of Heraklion, Crete, Greece
| | | |
Collapse
|
10
|
Yang YX, Yang X, Jiang XB, Lin L, Wang GY, Sun WZ, Zhang K, Li BH, Li H, Jia LC, Wei ZQ, Liu YF, Fu DN, Tang JX, Zhang W, Zhou JJ, Diao WC, Wang YJ, Chen XM, Xu CD, Lin LW, Wu JY, Wu JW, Peng LX, Pan JF, Liu BZ, Feng C, Huang XY, Zhou GQ, Sun Y. Artificial Intelligence-Empowered Multistep Integrated Radiation Therapy Workflow for Nasopharyngeal Carcinoma. Int J Radiat Oncol Biol Phys 2024:S0360-3016(24)03670-8. [PMID: 39708045 DOI: 10.1016/j.ijrobp.2024.11.096] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/12/2024] [Revised: 11/10/2024] [Accepted: 11/23/2024] [Indexed: 12/23/2024]
Abstract
PURPOSE To establish an artificial intelligence (AI)-empowered multistep integrated (MSI) radiation therapy (RT) workflow for patients with nasopharyngeal carcinoma (NPC) and evaluate its feasibility and clinical performance. METHODS AND MATERIALS Patients with NPC scheduled for MSI RT workflow were prospectively enrolled. This workflow integrates RT procedures from computed tomography (CT) scan to beam delivery, all performed with the patient on the treatment couch. Workflow performance, tumor response, patient-reported acute toxicities, and quality of life were evaluated. RESULTS From March 2022 to October 2023, 120 newly diagnosed, nonmetastatic patients with NPC were enrolled. Of these, 117 completed the workflow with a median duration of 23.2 minutes (range, 16.3-45.8). Median translation errors were 0.2 mm (from CT scan to planning approval) and 0.1 mm (during beam delivery). AI-generated contours required minimal revision for the high-risk clinical target volume and organs at risk, minor revision for the involved cervical lymph nodes and low-risk clinical target volume (median Dice similarity coefficients (DSC), 0.98 and 0.94), and more revision for the gross tumor at the primary site and the involved retropharyngeal lymph nodes (median DSC, 0.84). Of 117 AI-generated plans, 108 (92.3%) passed after the first optimization, with ≥97.8% of target volumes receiving ≥100% of the prescribed dose. Dosimetric constraints were met for most organs at risk, except the thyroid and submandibular glands. One hundred and fifteen patients achieved a complete response at week 12 post-RT, while 14 patients reported any acute toxicity as "very severe" from the start of RT to week 12 post-RT. CONCLUSIONS AI-empowered MSI RT workflow for patients with NPC is clinically feasible in a single institutional setting compared with standard, human-based RT workflow.
Collapse
Affiliation(s)
- Yu-Xian Yang
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Xin Yang
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Xiao-Bo Jiang
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Li Lin
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Guang-Yu Wang
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Wen-Zhao Sun
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Kang Zhang
- Shanghai United Imaging Healthcare Co., Ltd., Shanghai, China
| | - Bing-Huan Li
- Shanghai United Imaging Healthcare Co., Ltd., Shanghai, China
| | - Hua Li
- Shenzhen United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China
| | - Le-Cheng Jia
- Shenzhen United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China
| | - Zi-Quan Wei
- Shenzhen United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China
| | - Yan-Fei Liu
- Shenzhen United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China
| | - Dan-Ning Fu
- Shanghai United Imaging Healthcare Co., Ltd., Shanghai, China
| | - Jun-Xiang Tang
- Shanghai United Imaging Healthcare Co., Ltd., Shanghai, China
| | - Wei Zhang
- Shanghai United Imaging Healthcare Co., Ltd., Shanghai, China
| | - Jing-Jie Zhou
- Shanghai United Imaging Healthcare Co., Ltd., Shanghai, China
| | - Wen-Chao Diao
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Ya-Juan Wang
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Xue-Mei Chen
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Chen-Di Xu
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Liu-Wen Lin
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Jia-Ying Wu
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Jia-Wei Wu
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Li-Xia Peng
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Jin-Fa Pan
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Bing-Zhong Liu
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Chi Feng
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China
| | - Xiao-Yan Huang
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China.
| | - Guan-Qun Zhou
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China.
| | - Ying Sun
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, China.
| |
Collapse
|
11
|
Biswal SS, Sarkar B, Goyal M, Ganesh T, Shahid T, Bhattacharya J. An assessment of the influence of trade-off optimization in commercial knowledge based planning library creation for tongue cancer patients. Med Dosim 2024:S0958-3947(24)00058-X. [PMID: 39645424 DOI: 10.1016/j.meddos.2024.10.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2024] [Revised: 10/04/2024] [Accepted: 10/24/2024] [Indexed: 12/09/2024]
Abstract
This article aims to compare the dosimetric performance between knowledge-based plan (KBP) libraries with and without trade-off (TO) exploration using multicriterial optimization (MCO) for tongue cancer patients. The trade-off optimized library (KBP_MCO) contains a minimal number of constituent plans, whereas two nontrade-off optimized libraries contain a minimal and a large number of treatment plans, respectively. Three KBP libraries were created: KBP_100 and KBP_20, each comprising of 100 and 20 manually optimized plans, respectively. Additionally, another KBP library (KBP_MCO_20) was created by reoptimizing the constituent plans from KBP_20 using MCO techniques. A total of 70 tongue plans were validated through these libraries. Validation plans were evaluated for PTV and organ at risk (OAR) doses. Greenhouse-Geisser analysis (ANOVA) and the Bonferroni procedure (t-test) were used for statistical evaluation. The mean PTVD95% for KBP_100, KBP_20, and KBP_MCO_20 was 98.4% ± 0.3%, 98.9% ± 0.2%, and 98.7% ± 0.2%, respectively. The statistical significance of PTVD95% for the 3 possible combinations-KBP_100 vs KBP_20, KBP_100 vs KBP_MCO_20, and KBP_20 vs KBP_MCO_20 were statistically significant with p < 0.001. Spinal cord doses for KBP_100, KBP_20, and KBP_MCO_20 were 29.6 ± 1.8 Gy, 31.2 ± 2.5 Gy, and 26.8 ± 1.9 Gy, respectively, with p(KBP_100 vs KBP_20) = 0.14, p(KBP_100 vs KBP_MCO_20) = 0.001, and p(KBP_20 vs KBP_MCO_20) < 0.001. Only the first comparison showed a statistically insignificant variation. A trade-off optimized plan library with a minimal number of patients (20) yields better performance for serial structures (spinal cord and brainstem) compared to large manually optimized KBP libraries. For other organs at risk (OARs) and target dose coverage, although statistical differences were significant in most instances, the differences in physical dose were small and probably will not yield any significant clinical differences.
Collapse
Affiliation(s)
- Subhra S Biswal
- Department of Radiation Oncology, Apollo Multispeciality Hospitals, Kolkata, West Bengal, India; Depertment of Physics, GLA University, Mathura, Uttar Pradesh, India
| | - Biplab Sarkar
- Department of Radiation Oncology, Apollo Multispeciality Hospitals, Kolkata, West Bengal, India.
| | - Monika Goyal
- Depertment of Physics, GLA University, Mathura, Uttar Pradesh, India
| | - Tharmarnadar Ganesh
- Retired Professor, Department of Medical Physics, Manipal Hoapitals, New Delhi, India
| | - Tanweer Shahid
- Department of Radiation Oncology, Apollo Multispeciality Hospitals, Kolkata, West Bengal, India
| | - Jibak Bhattacharya
- Department of Radiation Oncology, Apollo Multispeciality Hospitals, Kolkata, West Bengal, India
| |
Collapse
|
12
|
Zhang J, Lei Y, Xia J, Chao M, Liu T. Federated learning for enhanced dose-volume parameter prediction with decentralized data. Med Phys 2024. [PMID: 39641909 DOI: 10.1002/mp.17566] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2024] [Revised: 11/12/2024] [Accepted: 11/28/2024] [Indexed: 12/07/2024] Open
Abstract
BACKGROUND The widespread adoption of knowledge-based planning in radiation oncology clinics is hindered by the lack of data and the difficulty associated with sharing medical data. PURPOSE This study aims to assess the feasibility of mitigating this challenge through federated learning (FL): a centralized model trained with distributed datasets, while keeping data localized and private. METHODS This concept was tested using 273 prostate 45 Gy plans. The cases were split into a training set with 220 cases and a validation set with 53 cases. The training set was further separated into 10 subsets to simulate treatment plans from different clinics. A gradient-boosting model was used to predict bladder and rectum V30Gy, V35Gy, and V40Gy. The Federated Averaging algorithm was employed to aggregate the individual model weights from distributed datasets. Grid search with five-fold in-training-set cross-validation was implemented to tune model hyperparameters. Additionally, we evaluated the robustness of the FL approach by varying the distribution of the training set data in several scenarios, including different number of sites and imbalanced data across sites. RESULTS The mean absolute error (MAE) for the FL model (4.7% ± 2.9%) is significantly lower than individual models trained separately (6.5% ± 4.9%, p < 0.001) and similar to a traditional centralized model (4.4% ± 2.8%, p = 0.14). The federated model is robust to the number of subsets, showing MAE of 4.7% ± 3.2%, 4.8% ± 3.1%, 4.8% ± 2.9%, 4.5% ± 2.8%, 4.9% ± 3.3%, and 4.8% ± 3.1% for 5, 10, 15, 20, 25, and 30 subsets, respectively. For the two imbalanced datasets, the FL model achieves MAEs of 4.5% ± 2.9% and 5.6% ± 4.0%, non-inferior to the balanced data model. For all bladder and rectum metrics, the FL model significantly outperforms 36.7% of individual models. CONCLUSIONS This study demonstrates the potential advantages of implementing a federated model over training individual models: the proposed FL approach achieves similar prediction accuracy as a conventional model without requiring centralized data storage. Even when local models struggle to produce accurate predictions due to data scarcity, the federated model consistently maintains high performance.
Collapse
Affiliation(s)
- Jiahan Zhang
- Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Yang Lei
- Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Junyi Xia
- Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Ming Chao
- Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Tian Liu
- Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| |
Collapse
|
13
|
Saito M, Kadoya N, Kimura Y, Nemoto H, Tozuka R, Jingu K, Onishi H. Evaluation of deep learning based dose prediction in head and neck cancer patients using two different types of input contours. J Appl Clin Med Phys 2024; 25:e14519. [PMID: 39285649 PMCID: PMC11633794 DOI: 10.1002/acm2.14519] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2024] [Revised: 08/17/2024] [Accepted: 08/20/2024] [Indexed: 12/12/2024] Open
Abstract
PURPOSE This study evaluates deep learning (DL) based dose prediction methods in head and neck cancer (HNC) patients using two types of input contours. MATERIALS AND METHODS Seventy-five HNC patients undergoing two-step volumetric-modulated arc therapy were included. Dose prediction was performed using the AIVOT prototype (AiRato.Inc, Sendai, Japan), a commercial software with an HD U-net-based dose distribution prediction system. Models were developed for the initial plan (46 Gy/23Fr) and boost plan (24 Gy/12Fr), trained with 65 cases and tested with 10 cases. The 8-channel model used one target (PTV) and seven organs at risk (OARs), while the 10-channel model added two dummy contours (PTV ring and spinal cord PRV). Predicted and deliverable doses, obtained through dose mimicking on another radiation treatment planning system, were evaluated using dose-volume indices for PTV and OARs. RESULTS For the initial plan, both models achieved approximately 2% prediction accuracy for the target dose and maintained accuracy within 3.2 Gy for OARs. The 10-channel model outperformed the 8-channel model for certain dose indices. For the boost plan, both models exhibited prediction accuracies of approximately 2% for the target dose and 1 Gy for OARs. The 10-channel model showed significantly closer predictions to the ground truth for D50% and Dmean. Deliverable plans based on prediction doses showed little significant difference compared to the ground truth, especially for the boost plan. CONCLUSION DL-based dose prediction using the AIVOT prototype software in HNC patients yielded promising results. While additional contours may enhance prediction accuracy, their impact on dose mimicking is relatively small.
Collapse
Affiliation(s)
- Masahide Saito
- Department of RadiologyUniversity of YamanashiYamanashiJapan
| | - Noriyuki Kadoya
- Department of Radiation OncologyTohoku Univ. Graduate School of MedicineSendaiJapan
| | - Yuto Kimura
- Radiation Oncology CenterOfuna Chuo HospitalKamakuraJapan
| | - Hikaru Nemoto
- Department of RadiologyUniversity of YamanashiYamanashiJapan
- Department of Radiation OncologyTohoku Univ. Graduate School of MedicineSendaiJapan
| | - Ryota Tozuka
- Department of RadiologyUniversity of YamanashiYamanashiJapan
- Department of Radiation OncologyTohoku Univ. Graduate School of MedicineSendaiJapan
| | - Keiichi Jingu
- Department of Radiation OncologyTohoku Univ. Graduate School of MedicineSendaiJapan
| | - Hiroshi Onishi
- Department of RadiologyUniversity of YamanashiYamanashiJapan
| |
Collapse
|
14
|
Szalkowski G, Xu X, Das S, Yap PT, Lian J. Automatic Treatment Planning for Radiation Therapy: A Cross-Modality and Protocol Study. Adv Radiat Oncol 2024; 9:101649. [PMID: 39553397 PMCID: PMC11566342 DOI: 10.1016/j.adro.2024.101649] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2024] [Accepted: 09/17/2024] [Indexed: 11/19/2024] Open
Abstract
Purpose This study investigated the applicability of 3-dimensional dose predictions from a model trained on one modality to a cross-modality automated planning workflow. Additionally, we explore the impact of integrating a multicriteria optimizer (MCO) on adapting predictions to different clinical preferences. Methods and Materials Using a previously created 3-stage U-Net in-house model trained on the 2020 American Association of Physicists in Medicine OpenKBP challenge data set (340 head and neck plans, all planned using 9-field static intensity modulated radiation therapy [IMRT]), we retrospectively generated dose predictions for 20 patients. These dose predictions were, in turn, used to generate deliverable IMRT, VMAT, and tomotherapy plans using the fallback plan functionality in Raystation. The deliverable plans were evaluated against the dose predictions based on primary clinical goals. A new set of plans was also generated using MCO-based optimization with predicted dose values as constraints. Delivery QA was performed on a subset of the plans to assure clinical deliverability. Results The mimicking approach accurately replicated the predicted dose distributions across different modalities, with slight deviations in the spinal cord and external contour maximum doses. MCO optimization significantly reduced doses to organs at risk, which were prioritized by our institution while maintaining target coverage. All tested plans met clinical deliverability standards, evidenced by a gamma analysis passing rate >98%. Conclusions Our findings show that a model trained only on IMRT plans can effectively contribute to planning across various modalities. Additionally, integrating predictions as constraints in an MCO-based workflow, rather than direct dose mimicking, enables a flexible, warm-start approach for treatment planning, although the benefit is reduced when the training set differs significantly from an institution's preference. Together, these approaches have the potential to significantly decrease plan turnaround time and quality variance, both at high-resource medical centers that can train in-house models and smaller centers that can adapt a model from another institution with minimal effort.
Collapse
Affiliation(s)
- Gregory Szalkowski
- Department of Radiation Oncology, University of North Carolina, Chapel Hill, North Carolina
- Department of Radiation Oncology, Stanford University, Stanford, California
| | - Xuanang Xu
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina, Chapel Hill, North Carolina
| | - Shiva Das
- Department of Radiation Oncology, University of North Carolina, Chapel Hill, North Carolina
| | - Pew-Thian Yap
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina, Chapel Hill, North Carolina
| | - Jun Lian
- Department of Radiation Oncology, University of North Carolina, Chapel Hill, North Carolina
| |
Collapse
|
15
|
Giraud P, Bibault JE. Artificial intelligence in radiotherapy: Current applications and future trends. Diagn Interv Imaging 2024; 105:475-480. [PMID: 38918124 DOI: 10.1016/j.diii.2024.06.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2024] [Revised: 05/31/2024] [Accepted: 06/01/2024] [Indexed: 06/27/2024]
Abstract
Radiation therapy has dramatically changed with the advent of computed tomography and intensity modulation. This added complexity to the workflow but allowed for more precise and reproducible treatment. As a result, these advances required the accurate delineation of many more volumes, raising questions about how to delineate them, in a uniform manner across centers. Then, as computing power improved, reverse planning became possible and three-dimensional dose distributions could be generated. Artificial intelligence offers the opportunity to make such workflow more efficient while increasing practice homogeneity. Many artificial intelligence-based tools are being implemented in routine practice to increase efficiency, reduce workload and improve homogeneity of treatments. Data retrieved from this workflow could be combined with clinical data and omic data to develop predictive tools to support clinical decision-making process. Such predictive tools are at the stage of proof-of-concept and need to be explainatory, prospectively validated, and based on large and multicenter cohorts. Nevertheless, they could bridge the gap to personalized radiation oncology, by personalizing oncologic strategies, dose prescriptions to tumor volumes and dose constraints to organs at risk.
Collapse
Affiliation(s)
- Paul Giraud
- INSERM UMR 1138, Centre de Recherche des Cordeliers, 75006 Paris, France; Department of Radiotherapy, Hôpital Européen Georges Pompidou, AP-HP, 75015 Paris, France; Université Paris Cité, Faculté de Médecine, 75006, Paris, France.
| | - Jean-Emmanuel Bibault
- Department of Radiotherapy, Hôpital Européen Georges Pompidou, AP-HP, 75015 Paris, France; Université Paris Cité, Faculté de Médecine, 75006, Paris, France
| |
Collapse
|
16
|
Miao Y, Li J, Ge R, Xie C, Liu Y, Zhang G, Miao M, Xu S. Dose prediction of CyberKnife Monte Carlo plan for lung cancer patients based on deep learning: robust learning of variable beam configurations. Radiat Oncol 2024; 19:170. [PMID: 39587661 PMCID: PMC11587619 DOI: 10.1186/s13014-024-02531-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2024] [Accepted: 09/25/2024] [Indexed: 11/27/2024] Open
Abstract
BACKGROUND Accurate calculation of lung cancer dose using the Monte Carlo (MC) algorithm in CyberKnife (CK) is essential for precise planning. We aim to employ deep learning to directly predict the 3D dose distribution calculated by the MC algorithm, enabling rapid and accurate automatic planning. However, most current methods solely focus on conventional intensity-modulated radiation therapy and assume a consistent beam configuration across all patients. This study seeks to develop a more versatile model incorporating variable beam configurations of CK and considering the patient's anatomy. METHODS This study proposed that the AB (anatomy and beam) model be compared with the control Mask (only anatomy) model. These models are based on a 3D U-Net network to investigate the impact of CK beam encoding information on dose prediction. The study collected 86 lung cancer patients who received CK's built-in MC algorithm plans using different beam configurations for training/validation (66 cases) and testing (20 cases). We compared the gamma passing rate, dose difference maps, and relevant dose-volume metrics to evaluate the model's performance. In addition, the Dice similarity coefficients (DSCs) were calculated to assess the spatial correspondence of isodose volumes. RESULTS The AB model demonstrated superior performance compared to the Mask model, particularly in the trajectory dose of the beam. The DSCs of the AB model were 20-40% higher than that of the Mask model in some dose regions. We achieved approximately 99% for the PTV and generally more than 95% for the organs at risk (OARs) referred to the clinical planning dose in the gamma passing rates (3 mm/3%). Relative to the Mask model, the AB model exhibited more than 90% improvement in small voxels (p < 0.001). The AB model matched well with the clinical plan's dose-volume histograms, and the average dose error for all organs was 1.65 ± 0.69%. CONCLUSIONS Our proposed new model signifies a crucial advancement in predicting CK 3D dose distributions for clinical applications. It enables planners to rapidly and precisely predict MC doses for lung cancer based on patient-specific beam configurations and optimize the CK treatment process.
Collapse
Affiliation(s)
- Yuchao Miao
- National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
- School of Physics, Beihang University, Beijing, China
- Department of Radiation Oncology, Fujian Medical University Union Hospital, Fuzhou, Fujian, China
| | - Jiwei Li
- ACCURAY, China National Nuclear Corporation, Tianjin, China
| | - Ruigang Ge
- Department of Radiation Oncology, The First Medical Center of the People's Liberation Army General Hospital, Beijing, China
| | - Chuanbin Xie
- Department of Radiation Oncology, The First Medical Center of the People's Liberation Army General Hospital, Beijing, China
| | - Yaoying Liu
- School of Physics, Beihang University, Beijing, China
| | - Gaolong Zhang
- School of Physics, Beihang University, Beijing, China
| | - Mingchang Miao
- Department of Radiation Oncology, the Fourth Hospital of Hebei Medical University, Shijiazhuang, Hebei, China
| | - Shouping Xu
- National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
| |
Collapse
|
17
|
Prunaretty J, Ungun B, Vauclin R, Costea M, Bus N, Paragios N, Fenoglietto P. Quantitative Evaluation of a Fully Automated Planning Solution for Prostate-Only and Whole-Pelvic Radiotherapy. Cancers (Basel) 2024; 16:3735. [PMID: 39594691 PMCID: PMC11591666 DOI: 10.3390/cancers16223735] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/03/2024] [Revised: 10/28/2024] [Accepted: 10/30/2024] [Indexed: 11/28/2024] Open
Abstract
Background/Objectives: To evaluate an end-to-end pipeline for normo-fractionated prostate-only and whole-pelvic cancer treatments that requires minimal human input and generates a machine-deliverable plan as an output. Methods: In collaboration with TheraPanacea, a treatment planning pipeline was developed that takes as its input a planning CT with organs-at-risk (OARs) and planning target volume (PTV) contours, the targeted linac machine, and the prescription dose. The primary components are (i) dose prediction by a single deep learning model for both localizations and (ii) a direct aperture VMAT plan optimization that seeks to mimic the predicted dose. The deep learning model was trained on 238 cases, and a held-out set of 86 cases was used for model validation. An end-to-end clinical evaluation study was performed on another 40 cases (20 prostate-only, 20 whole-pelvic). First, a quantitative evaluation was performed based on dose-volume histogram (DVH) points and plan parameter metrics. Then, the plan deliverability was assessed via portal dosimetry using the global gamma index. Additionally, the reference clinical manual plans were compared with the automated plans in terms of monitor unit (MU) numbers and modulation complexity scores (MCSv). Results: The automated plans provided adequate treatment plans (or minor deviations) with respect to the dose constraints, and the quality of the plans was similar to the manual plans for both localizations. Moreover, the automated plans showed successful deliverability and passed the portal dose verification. Despite higher median total MUs, no statistically significant correlation was observed between any of the gamma criteria tested and the number of MUs or MCSv. Conclusions: This study shows the feasibility of a deep learning-based fully automated treatment planning pipeline that generates high-quality plans that are competitive with manually made plans and are clinically approved in terms of dosimetry and machine deliverability.
Collapse
Affiliation(s)
| | - Baris Ungun
- TheraPanacea, 75004 Paris, France; (B.U.); (R.V.); (M.C.); (N.B.); (N.P.)
| | - Remi Vauclin
- TheraPanacea, 75004 Paris, France; (B.U.); (R.V.); (M.C.); (N.B.); (N.P.)
| | - Madalina Costea
- TheraPanacea, 75004 Paris, France; (B.U.); (R.V.); (M.C.); (N.B.); (N.P.)
| | - Norbert Bus
- TheraPanacea, 75004 Paris, France; (B.U.); (R.V.); (M.C.); (N.B.); (N.P.)
| | - Nikos Paragios
- TheraPanacea, 75004 Paris, France; (B.U.); (R.V.); (M.C.); (N.B.); (N.P.)
| | | |
Collapse
|
18
|
Zhang HW, Wang YH, Hu B, Pang HW. Uninvolved liver dose prediction in stereotactic body radiation therapy for liver cancer based on the neural network method. World J Gastrointest Oncol 2024; 16:4146-4156. [DOI: 10.4251/wjgo.v16.i10.4146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/12/2024] [Revised: 08/19/2024] [Accepted: 09/05/2024] [Indexed: 09/26/2024] Open
Abstract
BACKGROUND The quality of a radiotherapy plan often depends on the knowledge and expertise of the plan designers.
AIM To predict the uninvolved liver dose in stereotactic body radiotherapy (SBRT) for liver cancer using a neural network-based method.
METHODS A total of 114 SBRT plans for liver cancer were used to test the neural network method. Sub-organs of the uninvolved liver were automatically generated. Correlations between the volume of each sub-organ, uninvolved liver dose, and neural network prediction model were established using MATLAB. Of the cases, 70% were selected as the training set, 15% as the validation set, and 15% as the test set. The regression R-value and mean square error (MSE) were used to evaluate the model.
RESULTS The volume of the uninvolved liver was related to the volume of the corresponding sub-organs. For all sets of R-values of the prediction model, except for Dn0 which was 0.7513, all R-values of Dn10-Dn100 and Dnmean were > 0.8. The MSE of the prediction model was also low.
CONCLUSION We developed a neural network-based method to predict the uninvolved liver dose in SBRT for liver cancer. It is simple and easy to use and warrants further promotion and application.
Collapse
Affiliation(s)
- Huai-Wen Zhang
- Department of Radiotherapy, Jiangxi Cancer Hospital, Nanchang 330029, Jiangxi Province, China
| | - You-Hua Wang
- Department of Oncology, Gulin People’s Hospital, Luzhou 646500, Sichuan Province, China
| | - Bo Hu
- Key Laboratory of Nondestructive Testing (Ministry of Education), Nanchang Hang Kong University, Nanchang 330063, Jiangxi Province, China
| | - Hao-Wen Pang
- Department of Oncology, The Affiliated Hospital of Southwest Medical University, Luzhou 646000, Sichuan Province, China
| |
Collapse
|
19
|
Liao M, Di S, Zhao Y, Liang W, Yang Z. FA-Net: A hierarchical feature fusion and interactive attention-based network for dose prediction in liver cancer patients. Artif Intell Med 2024; 156:102961. [PMID: 39180923 DOI: 10.1016/j.artmed.2024.102961] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2023] [Revised: 07/07/2024] [Accepted: 08/16/2024] [Indexed: 08/27/2024]
Abstract
Dose prediction is a crucial step in automated radiotherapy planning for liver cancer. Several deep learning-based approaches for dose prediction have been proposed to enhance the design efficiency and quality of radiotherapy plan. However, these approaches usually take CT images and contours of organs at risk (OARs) and planning target volume (PTV) as a multi-channel input and is thus difficult to extract sufficient feature information from each input, which results in unsatisfactory dose distribution. In this paper, we propose a novel dose prediction network for liver cancer based on hierarchical feature fusion and interactive attention. A feature extraction module is first constructed to extract multi-scale features from different inputs, and a hierarchical feature fusion module is then built to fuse these multi-scale features hierarchically. A decoder based on attention mechanism is designed to gradually reconstruct the fused features into dose distribution. Additionally, we design an autoencoder network to generate a perceptual loss during training stage, which is used to improve the accuracy of dose prediction. The proposed method is tested on private clinical dataset and obtains HI and CI of 0.31 and 0.87, respectively. The experimental results are better than those by several existing methods, indicating that the dose distribution generated by the proposed method is close to that approved in clinics. The codes are available at https://github.com/hired-ld/FA-Net.
Collapse
Affiliation(s)
- Miao Liao
- School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, 411100, China
| | - Shuanhu Di
- College of Intelligence Science and Technology, National University of Defense Technology, Changsha, 410073, China.
| | - Yuqian Zhao
- School of Automation, Central South University, Changsha, 410083, China
| | - Wei Liang
- School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, 411100, China
| | - Zhen Yang
- Department of Oncology, Xiangya Hospital, Central South University, Changsha, 410031, China
| |
Collapse
|
20
|
Li C, Guo Y, Lin X, Feng X, Xu D, Yang R. Deep reinforcement learning in radiation therapy planning optimization: A comprehensive review. Phys Med 2024; 125:104498. [PMID: 39163802 DOI: 10.1016/j.ejmp.2024.104498] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/08/2024] [Revised: 07/08/2024] [Accepted: 08/06/2024] [Indexed: 08/22/2024] Open
Abstract
PURPOSE The formulation and optimization of radiation therapy plans are complex and time-consuming processes that heavily rely on the expertise of medical physicists. Consequently, there is an urgent need for automated optimization methods. Recent advancements in reinforcement learning, particularly deep reinforcement learning (DRL), show great promise for automating radiotherapy planning. This review summarizes the current state of DRL applications in this field, evaluates their effectiveness, and identifies challenges and future directions. METHODS A systematic search was conducted in Google Scholar, PubMed, IEEE Xplore, and Scopus using keywords such as "deep reinforcement learning", "radiation therapy", and "treatment planning". The extracted data were synthesized for an overview and critical analysis. RESULTS The application of deep reinforcement learning in radiation therapy plan optimization can generally be divided into three categories: optimizing treatment planning parameters, directly optimizing machine parameters, and adaptive radiotherapy. From the perspective of disease sites, DRL has been applied to cervical cancer, prostate cancer, vestibular schwannoma, and lung cancer. Regarding types of radiation therapy, it has been used in HDRBT, IMRT, SBRT, VMAT, GK, and Cyberknife. CONCLUSIONS Deep reinforcement learning technology has played a significant role in advancing the automated optimization of radiation therapy plans. However, there is still a considerable gap before it can be widely applied in clinical settings due to three main reasons: inefficiency, limited methods for quality assessment, and poor interpretability. To address these challenges, significant research opportunities exist in the future, such as constructing evaluators, parallelized training, and exploring continuous action spaces.
Collapse
Affiliation(s)
- Can Li
- Institute of Operations Research and Information Engineering, Beijing University of Technology, Beijing 100124, PR China
| | - Yuqi Guo
- Institute of Operations Research and Information Engineering, Beijing University of Technology, Beijing 100124, PR China
| | - Xinyan Lin
- Department of Radiation Oncology, Cancer Center, Peking University Third Hospital, Beijing, 100191, China; School of Physics, Beihang University, Beijing, 102206, China
| | - Xuezhen Feng
- Department of Radiation Oncology, Cancer Center, Peking University Third Hospital, Beijing, 100191, China; School of Nuclear Science and Technology, University of South China, Hengyang, 421001, China
| | - Dachuan Xu
- Institute of Operations Research and Information Engineering, Beijing University of Technology, Beijing 100124, PR China.
| | - Ruijie Yang
- Department of Radiation Oncology, Cancer Center, Peking University Third Hospital, Beijing, 100191, China.
| |
Collapse
|
21
|
Xiong T, Zeng G, Chen Z, Huang YH, Li B, Zhou D, Liu X, Sheng Y, Ren G, Wu QJ, Ge H, Cai J. Automatic planning for functional lung avoidance radiotherapy based on function-guided beam angle selection and plan optimization. Phys Med Biol 2024; 69:155007. [PMID: 38959907 DOI: 10.1088/1361-6560/ad5ef5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2024] [Accepted: 07/03/2024] [Indexed: 07/05/2024]
Abstract
Objective.This study aims to develop a fully automatic planning framework for functional lung avoidance radiotherapy (AP-FLART).Approach.The AP-FLART integrates a dosimetric score-based beam angle selection method and a meta-optimization-based plan optimization method, both of which incorporate lung function information to guide dose redirection from high functional lung (HFL) to low functional lung (LFL). It is applicable to both contour-based FLART (cFLART) and voxel-based FLART (vFLART) optimization options. A cohort of 18 lung cancer patient cases underwent planning-CT and SPECT perfusion scans were collected. AP-FLART was applied to generate conventional RT (ConvRT), cFLART, and vFLART plans for all cases. We compared automatic against manual ConvRT plans as well as automatic ConvRT against FLART plans, to evaluate the effectiveness of AP-FLART. Ablation studies were performed to evaluate the contribution of function-guided beam angle selection and plan optimization to dose redirection.Main results.Automatic ConvRT plans generated by AP-FLART exhibited similar quality compared to manual counterparts. Furthermore, compared to automatic ConvRT plans, HFL mean dose,V20, andV5were significantly reduced by 1.13 Gy (p< .001), 2.01% (p< .001), and 6.66% (p< .001) respectively for cFLART plans. Besides, vFLART plans showed a decrease in lung functionally weighted mean dose by 0.64 Gy (p< .01),fV20by 0.90% (p= 0.099), andfV5by 5.07% (p< .01) respectively. Though inferior conformity was observed, all dose constraints were well satisfied. The ablation study results indicated that both function-guided beam angle selection and plan optimization significantly contributed to dose redirection.Significance.AP-FLART can effectively redirect doses from HFL to LFL without severely degrading conventional dose metrics, producing high-quality FLART plans. It has the potential to advance the research and clinical application of FLART by providing labor-free, consistent, and high-quality plans.
Collapse
Affiliation(s)
- Tianyu Xiong
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China
| | - Guangping Zeng
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China
| | - Zhi Chen
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China
| | - Yu-Hua Huang
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China
| | - Bing Li
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University and Henan Cancer Hospital, Zhengzhou, People's Republic of China
| | - Dejun Zhou
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China
| | - Xi Liu
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China
| | - Yang Sheng
- Department of Radiation Oncology, Duke University Medical Center, Durham, NC, United States of America
| | - Ge Ren
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China
| | - Qingrong Jackie Wu
- Department of Radiation Oncology, Duke University Medical Center, Durham, NC, United States of America
| | - Hong Ge
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University and Henan Cancer Hospital, Zhengzhou, People's Republic of China
| | - Jing Cai
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China
| |
Collapse
|
22
|
Fu Q, Chen X, Liu Y, Zhang J, Xu Y, Yang X, Huang M, Men K, Dai J. Improvement of accumulated dose distribution in combined cervical cancer radiotherapy with deep learning-based dose prediction. Front Oncol 2024; 14:1407016. [PMID: 39040460 PMCID: PMC11260613 DOI: 10.3389/fonc.2024.1407016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2024] [Accepted: 06/17/2024] [Indexed: 07/24/2024] Open
Abstract
Purpose Difficulties remain in dose optimization and evaluation of cervical cancer radiotherapy that combines external beam radiotherapy (EBRT) and brachytherapy (BT). This study estimates and improves the accumulated dose distribution of EBRT and BT with deep learning-based dose prediction. Materials and methods A total of 30 patients treated with combined cervical cancer radiotherapy were enrolled in this study. The dose distributions of EBRT and BT plans were accumulated using commercial deformable image registration. A ResNet-101-based deep learning model was trained to predict pixel-wise dose distributions. To test the role of the predicted accumulated dose in clinic, each EBRT plan was designed using conventional method and then redesigned referencing the predicted accumulated dose distribution. Bladder and rectum dosimetric parameters and normal tissue complication probability (NTCP) values were calculated and compared between the conventional and redesigned accumulated doses. Results The redesigned accumulated doses showed a decrease in mean values of V50, V60, and D2cc for the bladder (-3.02%, -1.71%, and -1.19 Gy, respectively) and rectum (-4.82%, -1.97%, and -4.13 Gy, respectively). The mean NTCP values for the bladder and rectum were also decreased by 0.02‰ and 0.98%, respectively. All values had statistically significant differences (p < 0.01), except for the bladder D2cc (p = 0.112). Conclusion This study realized accumulated dose prediction for combined cervical cancer radiotherapy without knowing the BT dose. The predicted dose served as a reference for EBRT treatment planning, leading to a superior accumulated dose distribution and lower NTCP values.
Collapse
Affiliation(s)
- Qi Fu
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Xinyuan Chen
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Yuxiang Liu
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
- School of Physics and Technology, Wuhan University, Wuhan, China
| | - Jingbo Zhang
- Department of Radiotherapy Technology, The Cancer and Tuberculosis Hospital, Jiamusi, China
| | - Yingjie Xu
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Xi Yang
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Manni Huang
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Kuo Men
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Jianrong Dai
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| |
Collapse
|
23
|
Moore LC, Ahern F, Li L, Kallis K, Kisling K, Cortes KG, Nwachukwu C, Rash D, Yashar CM, Mayadev J, Zou J, Vasconcelos N, Meyers SM. Neural network dose prediction for cervical brachytherapy: Overcoming data scarcity for applicator-specific models. Med Phys 2024; 51:4591-4606. [PMID: 38814165 PMCID: PMC11309769 DOI: 10.1002/mp.17230] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2023] [Revised: 05/09/2024] [Accepted: 05/11/2024] [Indexed: 05/31/2024] Open
Abstract
BACKGROUND 3D neural network dose predictions are useful for automating brachytherapy (BT) treatment planning for cervical cancer. Cervical BT can be delivered with numerous applicators, which necessitates developing models that generalize to multiple applicator types. The variability and scarcity of data for any given applicator type poses challenges for deep learning. PURPOSE The goal of this work was to compare three methods of neural network training-a single model trained on all applicator data, fine-tuning the combined model to each applicator, and individual (IDV) applicator models-to determine the optimal method for dose prediction. METHODS Models were produced for four applicator types-tandem-and-ovoid (T&O), T&O with 1-7 needles (T&ON), tandem-and-ring (T&R) and T&R with 1-4 needles (T&RN). First, the combined model was trained on 859 treatment plans from 266 cervical cancer patients treated from 2010 onwards. The train/validation/test split was 70%/16%/14%, with approximately 49%/10%/19%/22% T&O/T&ON/T&R/T&RN in each dataset. Inputs included four channels for anatomical masks (high-risk clinical target volume [HRCTV], bladder, rectum, and sigmoid), a mask indicating dwell position locations, and applicator channels for each applicator component. Applicator channels were created by mapping the 3D dose for a single dwell position to each dwell position and summing over each applicator component with uniform dwell time weighting. A 3D Cascade U-Net, which consists of two U-Nets in sequence, and mean squared error loss function were used. The combined model was then fine-tuned to produce four applicator-specific models by freezing the first U-Net and encoding layers of the second and resuming training on applicator-specific data. Finally, four IDV models were trained using only data from each applicator type. Performance of these three model types was compared using the following metrics for the test set: mean error (ME, representing model bias) and mean absolute error (MAE) over all dose voxels and ME of clinical metrics (HRCTV D90% and D2cc of bladder, rectum, and sigmoid), averaged over all patients. A positive ME indicates the clinical dose was higher than predicted. 3D global gamma analysis with the prescription dose as reference value was performed. Dice similarity coefficients (DSC) were computed for each isodose volume. RESULTS Fine-tuned and combined models showed better performance than IDV applicator training. Fine-tuning resulted in modest improvements in about half the metrics, compared to the combined model, while the remainder were mostly unchanged. Fine-tuned MAE = 3.98%/2.69%/5.36%/3.80% for T&O/T&R/T&ON/T&RN, and ME over all voxels = -0.08%/-0.89%/-0.59%/1.42%. ME D2cc were bladder = -0.77%/1.00%/-0.66%/-1.53%, rectum = 1.11%/-0.22%/-0.29%/-3.37%, sigmoid = -0.47%/-0.06%/-2.37%/-1.40%, and ME D90 = 2.6%/-4.4%/4.8%/0.0%. Gamma pass rates (3%/3 mm) were 86%/91%/83%/89%. Mean DSCs were 0.92%/0.92%/0.88%/0.91% for isodoses ≤ 150% of prescription. CONCLUSIONS 3D BT dose was accurately predicted for all applicator types, as indicated by the low MAE and MEs, high gamma scores and high DSCs. Training on all treatment data overcomes challenges with data scarcity in each applicator type, resulting in superior performance than can be achieved by training on IDV applicators alone. This could presumably be explained by the fact that the larger, more diverse dataset allows the neural network to learn underlying trends and characteristics in dose that are common to all treatment applicators. Accurate, applicator-specific dose predictions could enable automated, knowledge-based planning for any cervical brachytherapy treatment.
Collapse
Affiliation(s)
- Lance C Moore
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Fritz Ahern
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Lingyi Li
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Karoline Kallis
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Kelly Kisling
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Katherina G Cortes
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Chika Nwachukwu
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Dominique Rash
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Catheryn M Yashar
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Jyoti Mayadev
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Jingjing Zou
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego and Moores Cancer Center, La Jolla, California, USA
| | - Nuno Vasconcelos
- Electrical and Computer Engineering, University of California San Diego, La Jolla, California, USA
| | - Sandra M Meyers
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| |
Collapse
|
24
|
Jiang C, Ji T, Qiao Q. Application and progress of artificial intelligence in radiation therapy dose prediction. Clin Transl Radiat Oncol 2024; 47:100792. [PMID: 38779524 PMCID: PMC11109740 DOI: 10.1016/j.ctro.2024.100792] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2024] [Accepted: 05/07/2024] [Indexed: 05/25/2024] Open
Abstract
Radiation therapy (RT) nowadays is a main treatment modality of cancer. To ensure the therapeutic efficacy of patients, accurate dose distribution is often required, which is a time-consuming and labor-intensive process. In addition, due to the differences in knowledge and experience among participants and diverse institutions, the predicted dose are often inconsistent. In last several decades, artificial intelligence (AI) has been applied in various aspects of RT, several products have been implemented in clinical practice and confirmed superiority. In this paper, we will review the research of AI in dose prediction, focusing on the progress in deep learning (DL).
Collapse
Affiliation(s)
- Chen Jiang
- Department of Radiation Oncology, The First Hospital of China Medical University, Shenyang, China
| | - Tianlong Ji
- Department of Radiation Oncology, The First Hospital of China Medical University, Shenyang, China
| | - Qiao Qiao
- Department of Radiation Oncology, The First Hospital of China Medical University, Shenyang, China
| |
Collapse
|
25
|
Wu Z, Jia X, Lu L, Xu C, Pang Y, Peng S, Liu M, Wu Y. Multi-center Dose Prediction Using Attention-aware Deep learning Algorithm Based on Transformers for Cervical Cancer Radiotherapy. Clin Oncol (R Coll Radiol) 2024; 36:e209-e223. [PMID: 38631974 DOI: 10.1016/j.clon.2024.03.022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2023] [Revised: 02/22/2024] [Accepted: 03/21/2024] [Indexed: 04/19/2024]
Abstract
AIMS Accurate dose delivery is crucial for cervical cancer volumetric modulated arc therapy (VMAT). We aimed to develop a robust deep-learning (DL) algorithm for fast and accurate dose prediction of cervical cancer VMAT in multicenter datasets and then explore the feasibility of the DL algorithm to endometrial cancer VMAT with different prescriptions. MATERIALS AND METHODS We proposed the AtTranNet algorithm for three-dimensional dose prediction. A total of 367 cervical patients were enrolled in this study. Three hundred twenty-two cervical patients from 3 centers were randomly divided into 70%, 10%, and 20% as training, validation, and testing sets, respectively. Forty-five cervical patients from another center were selected for external testing. Moreover, 70 patients of endometrial cancer with different prescriptions were further selected to test the model. Prediction precision was evaluated by dosimetric difference, dose map, and dose-volume histogram metrics. RESULTS The prediction results were all clinically acceptable. The mean absolute error within the body in internal testing was 0.66 ± 0.63%. The maximum |δD| for planning target volume was observed in D98, which is 1.24 ± 2.73 Gy. The maximum |δD| for organs at risk was observed in Dmean of bladder, which is 4.79 ± 3.14 Gy. The maximum |δV| were observed in V40 of pelvic bones, which is 4.77 ± 4.48%. CONCLUSION AtTranNet showed the feasibility and reasonable accuracy in the dose prediction for cervical cancer in multiple centers. The model can also be generalized for endometrial cancer with different prescriptions without any transfer learning.
Collapse
Affiliation(s)
- Z Wu
- Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University, Chongqing, PR China; Department of Radiotherapy, Zigong First People's Hospital, Sichuan, PR China; Yu-Yue Pathology Research Center, Jinfeng Laboratory, Chongqing, PR China
| | - X Jia
- Department of Radiotherapy, The Ninth People's Hospital Affiliated to Shanghai Jiaotong University School of Medicine, Shanghai, PR China
| | - L Lu
- Department of Radiotherapy, Tongling People's Hospital, Anhui, PR China
| | - C Xu
- Department of Radiotherapy, Beijing Luhe Hospital Affiliated to Capital Medical University, Beijing, PR China
| | - Y Pang
- Department of Radiotherapy, Zigong First People's Hospital, Sichuan, PR China
| | - S Peng
- Department of Radiotherapy, Zigong First People's Hospital, Sichuan, PR China
| | - M Liu
- Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University, Chongqing, PR China.
| | - Y Wu
- Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University, Chongqing, PR China; Yu-Yue Pathology Research Center, Jinfeng Laboratory, Chongqing, PR China.
| |
Collapse
|
26
|
Ma Y, Li Y, Xu P, Zhang H, Zhang X, Liu X, Li Q. A machine learning-based approach to predict energy layer for each field in spot-scanning proton arc therapy for lung cancer: A feasibility study. Med Phys 2024; 51:4970-4981. [PMID: 38772044 DOI: 10.1002/mp.17179] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2024] [Revised: 05/08/2024] [Accepted: 05/08/2024] [Indexed: 05/23/2024] Open
Abstract
BACKGROUND Determining the optimal energy layer (EL) for each field, under considering both dose constraints and delivery efficiency, is crucial to promoting the development of proton arc therapy (PAT) technology. PURPOSE This study aimed to explore the feasibility and potential clinical benefits of utilizing machine learning (ML) technique to automatically select EL for each field in PAT plans of lung cancer. METHODS Proton Bragg peak position (BPP) was employed to characterize EL. The ground truth BPPs for each field were determined using the modified ELO-SPAT framework. Features in geometric, water-equivalent thicknesses (WET) and beamlet were defined and extracted. By analyzing the relationship between the extracted features and ground truth, a polynomial regression model with L2-norm regularization (Ridge regression) was constructed and trained. The performance of the regression model was reported as an error between the predictions and the ground truth. Besides, the predictions were used to make PAT plans (PAT_PRED). These plans were compared with those using the ground truth BPPs (PAT_TRUTH) and the mid-WET of the target volumes (PAT_MID) in terms of relative biological effectiveness-weighted dose (RWD) distributions. One hundred ten patients with lung cancer, a total of 7920 samples, were enrolled retrospectively, with 5940 cases randomly selected as the training set and the remaining 1980 cases as the testing set. Nine patients (648 samples) were collected additionally to evaluate the regression model in terms of plan quality and robustness. RESULTS With regard to the prediction errors, the root mean squared errors and mean absolute errors between the ML-predicted and ground truth BPPs for the testing set were 9.165 and 6.572 mm, respectively, indicating differences of approximately two to three ELs. As for plan quality, the PAT_TRUTH and PAT_PRED plans performed similarly in terms of plan robustness, target coverage and organs at risk (OARs) protection, with differences smaller than 0.5 Gy(RBE). This trend was also observed for dose conformity and uniformity. The PAT_MID plans produced the lowest robustness index and lowest doses to OARs, along with the highest heterogeneity index, indicating better protection for OARs, improved plan robustness, but compromised dose homogeneity. Additionally, for relatively small tumor sizes, the PAT_MID plan demonstrated a notably poor dose conformity index. CONCLUSIONS Within this cohort under investigation, our study demonstrated the feasibility of using ML technique to predict ELs for each field, offering a fast (within 2 s) and memory-efficient reduced way to select ELs for PAT plan.
Collapse
Affiliation(s)
- Yuanyuan Ma
- Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Gansu Province, Lanzhou, China
- Putian Lanhai Nuclear Medicine Research Center, Putian, China
| | - Yazhou Li
- Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Gansu Province, Lanzhou, China
- University of Chinese Academy of Sciences, Beijing, China
- Gansu Provincial Hospital, Lanzhou, China
| | - Penghui Xu
- Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Gansu Province, Lanzhou, China
- Lanzhou University, Lanzhou, China
| | - Hui Zhang
- Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Gansu Province, Lanzhou, China
- Putian Lanhai Nuclear Medicine Research Center, Putian, China
| | - Xinyang Zhang
- Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Gansu Province, Lanzhou, China
- University of Chinese Academy of Sciences, Beijing, China
| | - Xinguo Liu
- Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Gansu Province, Lanzhou, China
- Putian Lanhai Nuclear Medicine Research Center, Putian, China
| | - Qiang Li
- Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, China
- Key Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Gansu Province, Lanzhou, China
- Putian Lanhai Nuclear Medicine Research Center, Putian, China
| |
Collapse
|
27
|
Prunaretty J, Lopez L, Cabaillé M, Bourgier C, Morel A, Azria D, Fenoglietto P. Evaluation of Ethos intelligent optimization engine for left locally advanced breast cancer. Front Oncol 2024; 14:1399978. [PMID: 39015493 PMCID: PMC11250590 DOI: 10.3389/fonc.2024.1399978] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/12/2024] [Accepted: 06/13/2024] [Indexed: 07/18/2024] Open
Abstract
Purpose To evaluate the feasibility to use a standard Ethos planning template to treat left-sided breast cancer with regional lymph nodes. Material/Methods The tuning cohort of 5 patients was used to create a planning template. The validation cohort included 15 patients treated for a locally advanced left breast cancer randomly enrolled. The Ethos planning template was tuned using standard 3 partial arc VMAT and two collimator rotation configurations: 45/285/345° and 30/60/330°. Re-planning was performed automatically using the template without editing. The study was conducted with a schedule of 42.3 Gy in 18 fractions to the breast/chestwall, internal mammary chain (IMC) and regional lymph nodes ("Nodes"). The PTV was defined as a 3D extension of the CTV with a margin of 7 mm, excluding the 5mm below the skin. The manual treatment plans were performed using Eclipse treatment planning system with AAA and PO algorithms (v15.6) and a manual arc VMAT configuration and imported in Ethos TPS (v1.1) for a dose calculation with Ethos Acuros algorithm. The automated plans were compared with the manual plans using PTV and CTV coverage, homogeneity and conformity indices (HI and CN) and doses to organs at risk (OAR) via DVH metrics. For each plan, the patient quality assurance (QA) were performed using Mobius3D and gamma index. Finally, two breast radiation oncologists performed a blinded assessment of the clinical acceptability of each of the three plans (manual and automated) for each patient. Results The manual and automated plans provided suitable treatment planning as regards dose constraints. The dosimetric comparison showed the CTV_breast D99% were significantly improved with both automated plans (p< 0,002) while PTV coverage was comparable. The doses to the organs at risk were equivalent for the three plans. Concerning treatment delivery, the Ethos-45° and Ethos-30° plans led to an increase in MUs compared to the manual plans, without affecting the beam on time. The average gamma index pass rates remained consistently above 98% regardless of the type of plan utilized. In the blinded evaluation, clinicians 1 and 2 assessed 13 out of 15 plans for Ethos 45° and 11 out of 15 plans for Ethos 30° as clinically acceptable. Conclusion Using a standard planning template for locally advanced breast cancer, the Ethos TPS provided automated plans that were clinically acceptable and comparable in quality to manually generated plans. Automated plans also dramatically reduce workflow and operator variability.
Collapse
Affiliation(s)
- Jessica Prunaretty
- Radiotherapy Department, Montpellier Regional Cancer Institute, Montpellier, France
| | | | | | | | | | | | | |
Collapse
|
28
|
Duan Y, Wang J, Wu P, Shao Y, Chen H, Wang H, Cao H, Gu H, Feng A, Huang Y, Shen Z, Lin Y, Kong Q, Liu J, Li H, Fu X, Yang Z, Cai X, Xu Z. AS-NeSt: A Novel 3D Deep Learning Model for Radiation Therapy Dose Distribution Prediction in Esophageal Cancer Treatment With Multiple Prescriptions. Int J Radiat Oncol Biol Phys 2024; 119:978-989. [PMID: 38159780 DOI: 10.1016/j.ijrobp.2023.12.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2023] [Revised: 11/06/2023] [Accepted: 12/03/2023] [Indexed: 01/03/2024]
Abstract
PURPOSE Implementing artificial intelligence technologies allows for the accurate prediction of radiation therapy dose distributions, enhancing treatment planning efficiency. However, esophageal cancers present unique challenges because of tumor complexity and diverse prescription types. Additionally, limited data availability hampers the effectiveness of existing artificial intelligence models. This study developed a deep learning model, trained on a diverse data set of esophageal cancer prescriptions, to improve dose prediction accuracy. METHODS AND MATERIALS We retrospectively collected data from 530 patients with esophageal cancer, including single-target and simultaneous integrated boost prescriptions, for model building. The proposed Asymmetric ResNeSt (AS-NeSt) model features novel 3-dimensional (3D) ResNeSt blocks and an asymmetrical architecture. We constructed a loss function targeting global and local doses and validated the model's performance against existing alternatives. Model-assisted experiments were used to validate its clinical benefits. RESULTS The AS-NeSt model maintained an absolute prediction error below 5% for each dosimetric metric. The average Dice similarity coefficient for isodose volumes was 0.93. The model achieved an average relative prediction error of 2.02%, statistically lower than Hierarchically Densely Connected U-net (4.17%), DoseNet (2.35%), and Densely Connected Network (3.65%). It also demonstrated significantly fewer parameters and shorter prediction times. Clinically, the AS-NeSt model raised physicians' ability to accurately preassess appropriate treatment methods before planning from 95.24% to 100%, reduced planning time by over 61% for junior dosimetrists and 52% for senior dosimetrists, and decreased both inter- and intra-dosimetrist discrepancies by more than 50%. CONCLUSIONS The AS-NeSt model, developed with innovative 3D ResNeSt blocks and an asymmetrical encoder-decoder structure, has been validated using clinical esophageal cancer patient data. It accurately predicts 3D dose distributions for various prescriptions, including simultaneous integrated boost, showing potential to improve the management of esophageal cancer treatment in a clinical setting.
Collapse
Affiliation(s)
- Yanhua Duan
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Institute of Modern Physics, Fudan University, Shanghai, China
| | - Jiyong Wang
- Shanghai Pulse Medical Technology Inc, Shanghai, China
| | - Puyu Wu
- Verisk Information Technology Ltd, Shanghai, China
| | - Yan Shao
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Hua Chen
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Hao Wang
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Hongbin Cao
- Department of Radiation Oncology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Hengle Gu
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Aihui Feng
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Institute of Modern Physics, Fudan University, Shanghai, China
| | - Ying Huang
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Institute of Modern Physics, Fudan University, Shanghai, China
| | - Zhenjiong Shen
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Yang Lin
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Qing Kong
- Institute of Modern Physics, Fudan University, Shanghai, China
| | - Jun Liu
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Hongxuan Li
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Xiaolong Fu
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Zhangru Yang
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| | - Xuwei Cai
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| | - Zhiyong Xu
- Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| |
Collapse
|
29
|
Guo Z, Lei L, Zhang Z, Du M, Chen Z. The potential of vascular normalization for sensitization to radiotherapy. Heliyon 2024; 10:e32598. [PMID: 38952362 PMCID: PMC11215263 DOI: 10.1016/j.heliyon.2024.e32598] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2024] [Revised: 05/11/2024] [Accepted: 06/05/2024] [Indexed: 07/03/2024] Open
Abstract
Radiotherapy causes apoptosis mainly through direct or indirect damage to DNA via ionizing radiation, leading to DNA strand breaks. However, the efficacy of radiotherapy is attenuated in malignant tumor microenvironment (TME), such as hypoxia. Tumor vasculature, due to the imbalance of various angiogenic and anti-angiogenic factors, leads to irregular morphology of tumor neovasculature, disordered arrangement of endothelial cells, and too little peripheral coverage. This ultimately leads to a TME characterized by hypoxia, low pH and high interstitial pressure. This deleterious TME further exacerbates the adverse effects of tumor neovascularization and weakens the efficacy of conventional radiotherapy. Whereas normalization of blood vessels improves TME and thus the efficacy of radiotherapy. In addition to describing the research progress of radiotherapy sensitization and vascular normalization, this review focuses on the strategy and application prospect of modulating vascular normalization to improve the efficacy of radiotherapy sensitization.
Collapse
Affiliation(s)
- Zhili Guo
- Key Laboratory of Medical Imaging Precision Theranostics and Radiation Protection, College of Hunan Province, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Changsha, China
- Institute of Medical Imaging, Hengyang Medical School, University of South China, Hengyang, China
- The Seventh Affiliated Hospital, Hunan Veterans Administration Hospital, Hengyang Medical School, University of South China, Changsha, Hunan, China
| | - Lingling Lei
- Key Laboratory of Medical Imaging Precision Theranostics and Radiation Protection, College of Hunan Province, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Changsha, China
- Institute of Medical Imaging, Hengyang Medical School, University of South China, Hengyang, China
| | - Zenan Zhang
- Key Laboratory of Medical Imaging Precision Theranostics and Radiation Protection, College of Hunan Province, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Changsha, China
- Institute of Medical Imaging, Hengyang Medical School, University of South China, Hengyang, China
- The Seventh Affiliated Hospital, Hunan Veterans Administration Hospital, Hengyang Medical School, University of South China, Changsha, Hunan, China
| | - Meng Du
- Key Laboratory of Medical Imaging Precision Theranostics and Radiation Protection, College of Hunan Province, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Changsha, China
- Institute of Medical Imaging, Hengyang Medical School, University of South China, Hengyang, China
| | - Zhiyi Chen
- Key Laboratory of Medical Imaging Precision Theranostics and Radiation Protection, College of Hunan Province, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Changsha, China
- Institute of Medical Imaging, Hengyang Medical School, University of South China, Hengyang, China
- The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Changsha, China
| |
Collapse
|
30
|
Leech M, Abdalqader A, Alexander S, Anderson N, Barbosa B, Callens D, Chapman V, Coffey M, Cox M, Curic I, Dean J, Denney E, Kearney M, Leung VW, Mortsiefer M, Nirgianaki E, Povilaitis J, Strikou D, Thompson K, van den Bosch M, Velec M, Woodford K, Buijs M. The Radiation Therapist profession through the lens of new technology: A practice development paper based on the ESTRO Radiation Therapist Workshops. Tech Innov Patient Support Radiat Oncol 2024; 30:100243. [PMID: 38831996 PMCID: PMC11145757 DOI: 10.1016/j.tipsro.2024.100243] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2024] [Accepted: 03/13/2024] [Indexed: 06/05/2024] Open
Abstract
Technological advances in radiation therapy impact on the role and scope of practice of the radiation therapist. The European Society of Radiotherapy and Oncology (ESTRO) recently held two workshops on this topic and this position paper reflects the outcome of this workshop, which included radiation therapists from all global regions. Workflows, quality assurance, research, IGRT and ART as well as clinical decision making are the areas of radiation therapist practice that will be highly influenced by advancing technology in the near future. This position paper captures the opportunities that this will bring to the radiation therapist profession, to the practice of radiation therapy and ultimately to patient care.
Collapse
Affiliation(s)
- Michelle Leech
- Applied Radiation Therapy Trinity, Discipline of Radiation Therapy, Trinity College Dublin, Ireland
- Trinity St. James’s Cancer Institute, Dublin, Ireland
| | | | - Sophie Alexander
- The Royal Marsden NHS Foundation Trust and The Institute of Cancer Research, Sutton, United Kingdom
| | - Nigel Anderson
- Department of Radiation Oncology, Olivia Newton-John Cancer Wellness & Research Centre - Austin Health, Heidelberg, Australia
| | - Barbara Barbosa
- Escola Internacional de Doutoramento, Universidad de Vigo, Spain
- Medical Physics, Radiobiology and Radiation Protection Group, IPO Porto Research Center (CI-IPOP), Porto Comprehensive Cancer Center (Porto.CCC) & Rise@CI-IPOP (Health Research Network), Porto, Portugal
| | - Dylan Callens
- University Hospital Leuven, Department of Radiation Oncology, Leuven, Belgium
- KU Leuven, Laboratory of Experimental Radiotherapy, Leuven, Belgium
| | | | - Mary Coffey
- Applied Radiation Therapy Trinity, Discipline of Radiation Therapy, Trinity College Dublin, Ireland
| | - Maya Cox
- Auckland City Hospital, Auckland, New Zealand
| | - Ilija Curic
- Radiosurgery and Stereotactic Radiotherapy Department, University Clinical Center of Serbia, Belgrade, Serbia
| | - Jenna Dean
- Department of Radiation Oncology, Olivia Newton-John Cancer Wellness & Research Centre - Austin Health, Heidelberg, Australia
| | | | - Maeve Kearney
- Applied Radiation Therapy Trinity, Discipline of Radiation Therapy, Trinity College Dublin, Ireland
- Trinity St. James’s Cancer Institute, Dublin, Ireland
| | - Vincent W.S. Leung
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong
| | | | | | - Justas Povilaitis
- The Hospital of Lithuanian University of Health Sciences Kauno klinikos, Kaunas, Lithuania
| | - Dimitra Strikou
- Radiation Oncology Unit, University and General Attikon Hospital, Athens, Greece
| | - Kenton Thompson
- Department of Radiation Therapy Services, Peter MacCallum Cancer Centre, Melbourne, Australia
| | | | - Michael Velec
- Princess Margaret Cancer Centre, University Health Network, Toronto, Canada
- Department of Radiation Oncology, University of Toronto, Toronto, Canada
| | - Katrina Woodford
- Department of Radiation Therapy Services, Peter MacCallum Cancer Centre, Melbourne, Australia
- Department of Medical Imaging and Radiation Sciences, Monash University, Clayton, Australia
| | - Monica Buijs
- InHolland Haarlem, University of Applied Science, Haarlem, the Netherlands
| |
Collapse
|
31
|
Hrinivich WT, Bhattacharya M, Mekki L, McNutt T, Jia X, Li H, Song DY, Lee J. Clinical VMAT machine parameter optimization for localized prostate cancer using deep reinforcement learning. Med Phys 2024; 51:3972-3984. [PMID: 38669457 DOI: 10.1002/mp.17100] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Revised: 03/20/2024] [Accepted: 04/14/2024] [Indexed: 04/28/2024] Open
Abstract
BACKGROUND Volumetric modulated arc therapy (VMAT) machine parameter optimization (MPO) remains computationally expensive and sensitive to input dose objectives creating challenges for manual and automatic planning. Reinforcement learning (RL) involves machine learning through extensive trial-and-error, demonstrating performance exceeding humans, and existing algorithms in several domains. PURPOSE To develop and evaluate an RL approach for VMAT MPO for localized prostate cancer to rapidly and automatically generate deliverable VMAT plans for a clinical linear accelerator (linac) and compare resultant dosimetry to clinical plans. METHODS We extended our previous RL approach to enable VMAT MPO of a 3D beam model for a clinical linac through a policy network. It accepts an input state describing the current control point and predicts continuous machine parameters for the next control point, which are used to update the input state, repeating until plan termination. RL training was conducted to minimize a dose-based cost function for prescription of 60 Gy in 20 fractions using CT scans and contours from 136 retrospective localized prostate cancer patients, 20 of which had existing plans used to initialize training. Data augmentation was employed to mitigate over-fitting, and parameter exploration was achieved using Gaussian perturbations. Following training, RL VMAT was applied to an independent cohort of 15 patients, and the resultant dosimetry was compared to clinical plans. We also combined the RL approach with our clinical treatment planning system (TPS) to automate final plan refinement, and creating the potential for manual review and edits as required for clinical use. RESULTS RL training was conducted for 5000 iterations, producing 40 000 plans during exploration. Mean ± SD execution time to produce deliverable VMAT plans in the test cohort was 3.3 ± 0.5 s which were automatically refined in the TPS taking an additional 77.4 ± 5.8 s. When normalized to provide equivalent target coverage, the RL+TPS plans provided a similar mean ± SD overall maximum dose of 63.2 ± 0.6 Gy and a lower mean rectum dose of 17.4 ± 7.4 compared to 63.9 ± 1.5 Gy (p = 0.061) and 21.0 ± 6.0 (p = 0.024) for the clinical plans. CONCLUSIONS An approach for VMAT MPO using RL for a clinical linac model was developed and applied to automatically generate deliverable plans for localized prostate cancer patients, and when combined with the clinical TPS shows potential to rapidly generate high-quality plans. The RL VMAT approach shows promise to discover advanced linac control policies through trial-and-error, and algorithm limitations and future directions are identified and discussed.
Collapse
Affiliation(s)
- William T Hrinivich
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland, USA
| | - Mahasweta Bhattacharya
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland, USA
| | - Lina Mekki
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland, USA
| | - Todd McNutt
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland, USA
| | - Xun Jia
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland, USA
| | - Heng Li
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland, USA
| | - Daniel Y Song
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland, USA
| | - Junghoon Lee
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland, USA
| |
Collapse
|
32
|
Tsai WT, Hsieh HL, Hung SK, Zeng CF, Lee MF, Lin PH, Lin CY, Li WC, Chiou WY, Wu TH. Dosimetry and efficiency comparison of knowledge-based and manual planning using volumetric modulated arc therapy for craniospinal irradiation. Radiol Oncol 2024; 58:289-299. [PMID: 38452341 PMCID: PMC11165983 DOI: 10.2478/raon-2024-0018] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2023] [Accepted: 01/03/2024] [Indexed: 03/09/2024] Open
Abstract
BACKGROUND Craniospinal irradiation (CSI) poses a challenge to treatment planning due to the large target, field junction, and multiple organs at risk (OARs) involved. The aim of this study was to evaluate the performance of knowledge-based planning (KBP) in CSI by comparing original manual plans (MP), KBP RapidPlan initial plans (RPI), and KBP RapidPlan final plans (RPF), which received further re-optimization to meet the dose constraints. PATIENTS AND METHODS Dose distributions in the target were evaluated in terms of coverage, mean dose, conformity index (CI), and homogeneity index (HI). The dosimetric results of OARs, planning time, and monitor unit (MU) were evaluated. RESULTS All MP and RPF plans met the plan goals, and 89.36% of RPI plans met the plan goals. The Wilcoxon tests showed comparable target coverage, CI, and HI for the MP and RPF groups; however, worst plan quality was demonstrated in the RPI plans than in MP and RPF. For the OARs, RPF and RPI groups had better dosimetric results than the MP group (P < 0.05 for optic nerves, eyes, parotid glands, and heart). The planning time was significantly reduced by the KBP from an average of 677.80 min in MP to 227.66 min (P < 0.05) and 307.76 min (P < 0.05) in RPI, and RPF, respectively. MU was not significantly different between these three groups. CONCLUSIONS The KBP can significantly reduce planning time in CSI. Manual re-optimization after the initial KBP is recommended to enhance the plan quality.
Collapse
Affiliation(s)
- Wei-Ta Tsai
- Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan
- Department of Radiation Oncology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi, Taiwan
| | - Hui-Ling Hsieh
- Department of Radiation Oncology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi, Taiwan
| | - Shih-Kai Hung
- Department of Radiation Oncology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi, Taiwan
- School of Medicine, Tzu Chi University, Hualien, Taiwan
| | - Chi-Fu Zeng
- Department of Radiation Oncology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi, Taiwan
| | - Ming-Fen Lee
- Department of Radiation Oncology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi, Taiwan
| | - Po-Hao Lin
- Department of Radiation Oncology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi, Taiwan
| | - Chia-Yi Lin
- Department of Radiation Oncology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi, Taiwan
| | - Wei-Chih Li
- Departments of Radiation Oncology, Taichung Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Taichung, Taiwan
| | - Wen-Yen Chiou
- Department of Radiation Oncology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi, Taiwan
- School of Medicine, Tzu Chi University, Hualien, Taiwan
| | - Tung-Hsin Wu
- Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan
| |
Collapse
|
33
|
Gao Y, Kyun Park Y, Jia X. Human-like intelligent automatic treatment planning of head and neck cancer radiation therapy. Phys Med Biol 2024; 69:115049. [PMID: 38744304 PMCID: PMC11148880 DOI: 10.1088/1361-6560/ad4b90] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2024] [Revised: 04/26/2024] [Accepted: 05/14/2024] [Indexed: 05/16/2024]
Abstract
Objective.Automatic treatment planning of radiation therapy (RT) is desired to ensure plan quality, improve planning efficiency, and reduce human errors. We have proposed an Intelligent Automatic Treatment Planning framework with a virtual treatment planner (VTP), an artificial intelligence robot built using deep reinforcement learning, autonomously operating a treatment planning system (TPS). This study extends our previous successes in relatively simple prostate cancer RT planning to head-and-neck (H&N) cancer, a more challenging context even for human planners due to multiple prescription levels, proximity of targets to critical organs, and tight dosimetric constraints.Approach.We integrated VTP with a real clinical TPS to establish a fully automated planning workflow guided by VTP. This integration allowed direct model training and evaluation using the clinical TPS. We designed the VTP network structure to approach the decision-making process in RT planning in a hierarchical manner that mirrors human planners. The VTP network was trained via theQ-learning framework. To assess the effectiveness of VTP, we conducted a prospective evaluation in the 2023 Planning Challenge organized by the American Association of Medical Dosimetrists (AAMD). We extended our evaluation to include 20 clinical H&N cancer patients, comparing the plans generated by VTP against their clinical plans.Main results.In the prospective evaluation for the AAMD Planning Challenge, VTP achieved a plan score of 139.08 in the initial phase evaluating plan quality, and 15 min of planning time with the first place ranking in the adaptive phase competing for planning efficiency while meeting all plan quality requirements. For clinical cases, VTP-generated plans achieved an average VTP score of125.33±11.12, which outperformed the corresponding clinical plans with an average score of117.76±13.56.Significance.We successfully integrated VTP with the clinical TPS to achieve a fully automated treatment planning workflow. The compelling performance of VTP demonstrated its potential in automating H&N cancer RT planning.
Collapse
Affiliation(s)
- Yin Gao
- Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, United States of America
| | - Yang Kyun Park
- Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, United States of America
| | - Xun Jia
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, United States of America
| |
Collapse
|
34
|
Biswal SS, Sarkar B, Goyal M. Determining the library size for the optimal output plan in the RapidPlan knowledge-based planning system using multicriteria optimization. Br J Radiol 2024; 97:1153-1161. [PMID: 38637944 PMCID: PMC11135798 DOI: 10.1093/bjr/tqae084] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Revised: 03/06/2024] [Accepted: 04/16/2024] [Indexed: 04/20/2024] Open
Abstract
OBJECTIVES The aim of this study was to determine the number of trade-off explored (TO) library plans required for building a RapidPlan (RP) library that would generate the optimal clinical treatment plan. METHODS We developed 2 RP models, 1 each for the 2 clinical sites, head and neck (HN) and cervix. The models were created using 100 plans and were validated using 70 plans (VP) for each site respectively. Each of the 2 libraries comprising 100 TO plans was divided into 5 different subsets of library plans comprising 20, 40, 60, 80, and 100 plans, leading to 5 different RP models for each site. For every validation patient, a TO plan (TO_VP) was created. For every patient, 5 RP plans were automatically generated using RP models. The dosimetric parameters of the 6 plans (TO_VP + 5 RP plans) were compared using Pearson correlation and Greenhouse-Geisser analysis. RESULTS Planning target volume (PTV) dose volume parameters PTVD95% in 6 competing plans varied between 97.6 ± 0.7% and 98.1 ± 0.6% in HN cases and 98.8 ± 0.3% and 99.0 ± 0.4% in cervix cases. Overall, for both sites, the mean variations in organ at risk (OAR) doses or volumes were within 50 cGy, 0.5%, and 0.2 cc between library plans, and if TO_VP was included the variations deteriorated to 180 cGy, 0.4%, and 15 cc. All OARs in both sites, except D0.1 ccspine, showed a statistically insignificant variation between all plans. CONCLUSIONS Dosimetric variation among various output plans generated from 5 RP libraries is minimal and clinically insignificant. The optimal output plan can be derived from the least-weighted library consisting of 20 plans. ADVANCES IN KNOWLEDGE This article shows that, when the constituent plans are subjected to trade-off exploration, the number of constituent plans for a knowledge-based planning module is not relevant in terms of its dosimetric output.
Collapse
Affiliation(s)
- Subhra S Biswal
- Department of Radiation Oncology, Apollo Multispeciality Hospitals, Kolkata, West Bengal-700054, India
- Institute of Applied Science and Humanities, GLA University, Mathura, UP-281406, India
| | - Biplab Sarkar
- Department of Radiation Oncology, Apollo Multispeciality Hospitals, Kolkata, West Bengal-700054, India
- Institute of Applied Science and Humanities, GLA University, Mathura, UP-281406, India
| | - Monika Goyal
- Institute of Applied Science and Humanities, GLA University, Mathura, UP-281406, India
| |
Collapse
|
35
|
Wang D, Geng H, Gondi V, Lee NY, Tsien CI, Xia P, Chenevert TL, Michalski JM, Gilbert MR, Le QT, Omuro AM, Men K, Aldape KD, Cao Y, Srinivasan A, Barani IJ, Sachdev S, Huang J, Choi S, Shi W, Battiste JD, Wardak Z, Chan MD, Mehta MP, Xiao Y. Radiotherapy Plan Quality Assurance in NRG Oncology Trials for Brain and Head/Neck Cancers: An AI-Enhanced Knowledge-Based Approach. Cancers (Basel) 2024; 16:2007. [PMID: 38893130 PMCID: PMC11171017 DOI: 10.3390/cancers16112007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2024] [Revised: 05/15/2024] [Accepted: 05/19/2024] [Indexed: 06/21/2024] Open
Abstract
The quality of radiation therapy (RT) treatment plans directly affects the outcomes of clinical trials. KBP solutions have been utilized in RT plan quality assurance (QA). In this study, we evaluated the quality of RT plans for brain and head/neck cancers enrolled in multi-institutional clinical trials utilizing a KBP approach. The evaluation was conducted on 203 glioblastoma (GBM) patients enrolled in NRG-BN001 and 70 nasopharyngeal carcinoma (NPC) patients enrolled in NRG-HN001. For each trial, fifty high-quality photon plans were utilized to build a KBP photon model. A KBP proton model was generated using intensity-modulated proton therapy (IMPT) plans generated on 50 patients originally treated with photon RT. These models were then applied to generate KBP plans for the remaining patients, which were compared against the submitted plans for quality evaluation, including in terms of protocol compliance, target coverage, and organ-at-risk (OAR) doses. RT plans generated by the KBP models were demonstrated to have superior quality compared to the submitted plans. KBP IMPT plans can decrease the variation of proton plan quality and could possibly be used as a tool for developing improved plans in the future. Additionally, the KBP tool proved to be an effective instrument for RT plan QA in multi-center clinical trials.
Collapse
Affiliation(s)
- Du Wang
- Department of Radiation Oncology, University of Pennsylvania, Philadelphia, PA 19104, USA (Y.X.)
| | - Huaizhi Geng
- Department of Radiation Oncology, University of Pennsylvania, Philadelphia, PA 19104, USA (Y.X.)
| | - Vinai Gondi
- Northwestern Medicine Cancer Center Warrenville, Warrenville, IL 60555, USA
| | - Nancy Y. Lee
- Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | | | - Ping Xia
- Cleveland Clinic Foundation, Cleveland, OH 44195, USA
| | - Thomas L. Chenevert
- Department of Radiology, University of Michigan, Ann Arbor, MI 48109, USA; (T.L.C.)
| | - Jeff M. Michalski
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO 63110, USA
| | | | - Quynh-Thu Le
- Stanford Cancer Institute, Stanford, CA 94305, USA; (Q.-T.L.)
| | | | - Kuo Men
- Department of Radiation Oncology, University of Pennsylvania, Philadelphia, PA 19104, USA (Y.X.)
| | | | - Yue Cao
- Department of Radiology, University of Michigan, Ann Arbor, MI 48109, USA; (T.L.C.)
| | - Ashok Srinivasan
- Department of Radiology, University of Michigan, Ann Arbor, MI 48109, USA; (T.L.C.)
| | - Igor J. Barani
- Saint Joseph’s Hospital and Medical Center, Phoenix, AZ 85013, USA
| | - Sean Sachdev
- Northwestern Medicine Cancer Center Warrenville, Warrenville, IL 60555, USA
| | - Jiayi Huang
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO 63110, USA
| | - Serah Choi
- UPMC-Shadyside Hospital, Case Western Reserve University, Pittsburgh, PA 15232, USA
| | - Wenyin Shi
- Department of Radiation Oncology, Thomas Jefferson University Hospital, Philadelphia, PA 19107, USA
| | - James D. Battiste
- Stephenson Cancer Center, University of Oklahoma Health Sciences Center, Oklahoma City, OK 73104, USA
| | - Zabi Wardak
- UT Southwestern, Simmons Cancer Center, Dallas, TX 75235, USA
| | - Michael D. Chan
- Baptist Comprehensive Cancer Center, Wake Forest University Health Sciences, Winston-Salem, NC 27157, USA
| | | | - Ying Xiao
- Department of Radiation Oncology, University of Pennsylvania, Philadelphia, PA 19104, USA (Y.X.)
| |
Collapse
|
36
|
Zhang B, Babier A, Ruschin M, Chan TCY. Knowledge-based planning for Gamma Knife. Med Phys 2024; 51:3207-3219. [PMID: 38598107 DOI: 10.1002/mp.17058] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2023] [Revised: 03/13/2024] [Accepted: 03/21/2024] [Indexed: 04/11/2024] Open
Abstract
BACKGROUND Current methods for Gamma Knife (GK) treatment planning utilizes either manual forward planning, where planners manually place shots in a tumor to achieve a desired dose distribution, or inverse planning, whereby the dose delivered to a tumor is optimized for multiple objectives based on established metrics. For other treatment modalities like IMRT and VMAT, there has been a recent push to develop knowledge-based planning (KBP) pipelines to address the limitations presented by forward and inverse planning. However, no complete KBP pipeline has been created for GK. PURPOSE To develop a novel (KBP) pipeline, using inverse optimization (IO) with 3D dose predictions for GK. METHODS Data were obtained for 349 patients from Sunnybrook Health Sciences Centre. A 3D dose prediction model was trained using 322 patients, based on a previously published deep learning methodology, and dose predictions were generated for the remaining 27 out-of-sample patients. A generalized IO model was developed to learn objective function weights from dose predictions. These weights were then used in an inverse planning model to generate deliverable treatment plans. A dose mimicking (DM) model was also implemented for comparison. The quality of the resulting plans was compared to their clinical counterparts using standard GK quality metrics. The performance of the models was also characterized with respect to the dose predictions. RESULTS Across all quality metrics, plans generated using the IO pipeline performed at least as well as or better than the respective clinical plans. The average conformity and gradient indices of IO plans was 0.737 ± $\pm$ 0.158 and 3.356 ± $\pm$ 1.030 respectively, compared to 0.713 ± $\pm$ 0.124 and 3.452 ± $\pm$ 1.123 for the clinical plans. IO plans also performed better than DM plans for five of the six quality metrics. Plans generated using IO also have average treatment times comparable to that of clinical plans. With regards to the dose predictions, predictions with higher conformity tend to result in higher quality KBP plans. CONCLUSIONS Plans resulting from an IO KBP pipeline are, on average, of equal or superior quality compared to those obtained through manual planning. The results demonstrate the potential for the use of KBP to generate GK treatment with minimal human intervention.
Collapse
Affiliation(s)
- Binghao Zhang
- Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Ontario, Canada
| | - Aaron Babier
- Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Ontario, Canada
| | - Mark Ruschin
- Odette Cancer Centre, Sunnybrook Health Sciences Centre, Toronto, Ontario, Canada
| | - Timothy C Y Chan
- Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Ontario, Canada
| |
Collapse
|
37
|
Scaggion A, Cavinato S, Dusi F, El Khouzai B, Guida F, Paronetto C, Rossato MA, Sapignoli S, Scott ASA, Sepulcri M, Paiusco M. On the necessity of specialized knowledge-based models for SBRT prostate treatments plans. Phys Med 2024; 121:103364. [PMID: 38701626 DOI: 10.1016/j.ejmp.2024.103364] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/06/2023] [Revised: 03/21/2024] [Accepted: 04/19/2024] [Indexed: 05/05/2024] Open
Abstract
PURPOSE Test whether a well-grounded KBP model trained on moderately hypo-fractionated prostate treatments can be used to satisfactorily drive the optimization of SBRT prostate treatments. MATERIALS AND METHODS A KBP model (SBRT-model) was developed, trained and validated using the first forty-seven clinically treated VMAT SBRT prostate plans (42.7 Gy/7fx or 36.25 Gy/5fx). The performance and robustness of this model were compared against a high-quality KBP-model (ST-model) that was already clinically adopted for hypo-fractionated (70 Gy/28fx and 60 Gy/20fx) prostate treatments. The two models were compared in terms of their predictions robustness, and the quality of their outcomes were evaluated against a set of reference clinical SBRT plans. Plan quality was assessed using DVH metrics, blinded clinical ranking, and a dedicated Plan Quality Metric algorithm. RESULTS The plan libraries of the two models were found to share a high degree of anatomical similarity. The overall quality (APQM%) of the plans obtained both with the ST- and SBRT-models was compatible with that of the original clinical plans, namely (93.7 ± 4.1)% and (91.6 ± 3.9)% vs (92.8.9 ± 3.6)%. Plans obtained with the ST-model showed significantly higher target coverage (PTV V95%): (97.9 ± 0.8)% vs (97.1 ± 0.9)% (p < 0.05). Conversely, plans optimized following the SBRT-model showed a small but not-clinically relevant increase in OAR sparing. ST-model generally provided more reliable predictions than SBRT-model. Two radiation oncologists judged as equivalent the plans based on the KBP prediction, which was also judged better that reference clinical plans. CONCLUSION A KBP model trained on moderately fractionated prostate treatment plans provided optimal SBRT prostate plans, with similar or larger plan quality than an embryonic SBRT-model based on a limited number of cases.
Collapse
Affiliation(s)
- Alessandro Scaggion
- S.C. Fisica Sanitaria, Istituto Oncologico Veneto IOV - IRCCS, Padova, Italy.
| | - Samuele Cavinato
- S.C. Fisica Sanitaria, Istituto Oncologico Veneto IOV - IRCCS, Padova, Italy
| | - Francesca Dusi
- S.C. Fisica Sanitaria, Istituto Oncologico Veneto IOV - IRCCS, Padova, Italy
| | - Badr El Khouzai
- S.C. Radioterapia, Istituto Oncologico Veneto IOV - IRCCS, Padova, Italy
| | - Federica Guida
- S.C. Fisica Sanitaria, Istituto Oncologico Veneto IOV - IRCCS, Padova, Italy
| | - Chiara Paronetto
- S.C. Radioterapia, Istituto Oncologico Veneto IOV - IRCCS, Padova, Italy
| | | | - Sonia Sapignoli
- S.C. Fisica Sanitaria, Istituto Oncologico Veneto IOV - IRCCS, Padova, Italy
| | | | - Matteo Sepulcri
- S.C. Radioterapia, Istituto Oncologico Veneto IOV - IRCCS, Padova, Italy
| | - Marta Paiusco
- S.C. Fisica Sanitaria, Istituto Oncologico Veneto IOV - IRCCS, Padova, Italy
| |
Collapse
|
38
|
Gao Y, Gonzalez Y, Nwachukwu C, Albuquerque K, Jia X. Predicting treatment plan approval probability for high-dose-rate brachytherapy of cervical cancer using adversarial deep learning. Phys Med Biol 2024; 69:095010. [PMID: 38537309 PMCID: PMC11023000 DOI: 10.1088/1361-6560/ad3880] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2023] [Revised: 03/08/2024] [Accepted: 03/26/2024] [Indexed: 04/18/2024]
Abstract
Objective.Predicting the probability of having the plan approved by the physician is important for automatic treatment planning. Driven by the mathematical foundation of deep learning that can use a deep neural network to represent functions accurately and flexibly, we developed a deep-learning framework that learns the probability of plan approval for cervical cancer high-dose-rate brachytherapy (HDRBT).Approach.The system consisted of a dose prediction network (DPN) and a plan-approval probability network (PPN). DPN predicts organs at risk (OAR)D2ccand CTVD90%of the current fraction from the patient's current anatomy and prescription dose of HDRBT. PPN outputs the probability of a given plan being acceptable to the physician based on the patients anatomy and the total dose combining HDRBT and external beam radiotherapy sessions. Training of the networks was achieved by first training them separately for a good initialization, and then jointly via an adversarial process. We collected approved treatment plans of 248 treatment fractions from 63 patients. Among them, 216 plans from 54 patients were employed in a four-fold cross validation study, and the remaining 32 plans from other 9 patients were saved for independent testing.Main results.DPN predicted equivalent dose of 2 Gy for bladder, rectum, sigmoidD2ccand CTVD90%with a relative error of 11.51% ± 6.92%, 8.23% ± 5.75%, 7.12% ± 6.00%, and 10.16% ± 10.42%, respectively. In a task that differentiates clinically approved plans and disapproved plans generated by perturbing doses in ground truth approved plans by 20%, PPN achieved accuracy, sensitivity, specificity, and area under the curve 0.70, 0.74, 0.65, and 0.74.Significance.We demonstrated the feasibility of developing a novel deep-learning framework that predicts a probability of plan approval for HDRBT of cervical cancer, which is an essential component in automatic treatment planning.
Collapse
Affiliation(s)
- Yin Gao
- Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, United States of America
| | - Yesenia Gonzalez
- Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, United States of America
| | - Chika Nwachukwu
- Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, United States of America
| | - Kevin Albuquerque
- Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, United States of America
| | - Xun Jia
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, United States of America
| |
Collapse
|
39
|
Wheeler PA, West NS, Powis R, Maggs R, Chu M, Pearson RA, Willis N, Kurec B, Reed KL, Lewis DG, Staffurth J, Spezi E, Millin AE. Multi-institutional evaluation of a Pareto navigation guided automated radiotherapy planning solution for prostate cancer. Radiat Oncol 2024; 19:45. [PMID: 38589961 PMCID: PMC11003074 DOI: 10.1186/s13014-024-02404-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2022] [Accepted: 01/15/2024] [Indexed: 04/10/2024] Open
Abstract
BACKGROUND Current automated planning solutions are calibrated using trial and error or machine learning on historical datasets. Neither method allows for the intuitive exploration of differing trade-off options during calibration, which may aid in ensuring automated solutions align with clinical preference. Pareto navigation provides this functionality and offers a potential calibration alternative. The purpose of this study was to validate an automated radiotherapy planning solution with a novel multi-dimensional Pareto navigation calibration interface across two external institutions for prostate cancer. METHODS The implemented 'Pareto Guided Automated Planning' (PGAP) methodology was developed in RayStation using scripting and consisted of a Pareto navigation calibration interface built upon a 'Protocol Based Automatic Iterative Optimisation' planning framework. 30 previous patients were randomly selected by each institution (IA and IB), 10 for calibration and 20 for validation. Utilising the Pareto navigation interface automated protocols were calibrated to the institutions' clinical preferences. A single automated plan (VMATAuto) was generated for each validation patient with plan quality compared against the previously treated clinical plan (VMATClinical) both quantitatively, using a range of DVH metrics, and qualitatively through blind review at the external institution. RESULTS PGAP led to marked improvements across the majority of rectal dose metrics, with Dmean reduced by 3.7 Gy and 1.8 Gy for IA and IB respectively (p < 0.001). For bladder, results were mixed with low and intermediate dose metrics reduced for IB but increased for IA. Differences, whilst statistically significant (p < 0.05) were small and not considered clinically relevant. The reduction in rectum dose was not at the expense of PTV coverage (D98% was generally improved with VMATAuto), but was somewhat detrimental to PTV conformality. The prioritisation of rectum over conformality was however aligned with preferences expressed during calibration and was a key driver in both institutions demonstrating a clear preference towards VMATAuto, with 31/40 considered superior to VMATClinical upon blind review. CONCLUSIONS PGAP enabled intuitive adaptation of automated protocols to an institution's planning aims and yielded plans more congruent with the institution's clinical preference than the locally produced manual clinical plans.
Collapse
Affiliation(s)
- Philip A Wheeler
- Radiotherapy Physics Department, Velindre Cancer Centre, CF14 2TL, Cardiff, Wales, UK.
| | - Nicholas S West
- Northern Centre for Cancer Care, Cancer Services and Clinical Haematology, Newcastle upon Tyne, UK
| | - Richard Powis
- Worcester Oncology Centre, Worcestershire Acute Hospitals NHS Trust, Worcester, UK
| | - Rhydian Maggs
- Radiotherapy Physics Department, Velindre Cancer Centre, CF14 2TL, Cardiff, Wales, UK
| | - Michael Chu
- Radiotherapy Physics Department, Velindre Cancer Centre, CF14 2TL, Cardiff, Wales, UK
| | - Rachel A Pearson
- Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University Centre for Cancer, Newcastle University, Newcastle upon Tyne, UK
| | - Nick Willis
- Northern Centre for Cancer Care, Cancer Services and Clinical Haematology, Newcastle upon Tyne, UK
| | - Bartlomiej Kurec
- Worcester Oncology Centre, Worcestershire Acute Hospitals NHS Trust, Worcester, UK
| | - Katie L Reed
- Worcester Oncology Centre, Worcestershire Acute Hospitals NHS Trust, Worcester, UK
| | - David G Lewis
- Radiotherapy Physics Department, Velindre Cancer Centre, CF14 2TL, Cardiff, Wales, UK
| | - John Staffurth
- School of Medicine, Cardiff University, Cardiff, Wales, UK
- Velindre Cancer Centre, Medical Directorate, Cardiff, Wales, UK
| | - Emiliano Spezi
- School of Engineering, Cardiff University, Cardiff, Wales, UK
| | - Anthony E Millin
- Radiotherapy Physics Department, Velindre Cancer Centre, CF14 2TL, Cardiff, Wales, UK
| |
Collapse
|
40
|
Castriconi R, Tudda A, Placidi L, Benecchi G, Cagni E, Dusi F, Ianiro A, Landoni V, Malatesta T, Mazzilli A, Meffe G, Oliviero C, Rambaldi Guidasci G, Scaggion A, Trojani V, Del Vecchio A, Fiorino C. Inter-institutional variability of knowledge-based plan prediction of left whole breast irradiation. Phys Med 2024; 120:103331. [PMID: 38484461 DOI: 10.1016/j.ejmp.2024.103331] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/03/2023] [Revised: 02/05/2024] [Accepted: 03/08/2024] [Indexed: 04/19/2024] Open
Abstract
PURPOSE Within a multi-institutional project, we aimed to assess the transferability of knowledge-based (KB) plan prediction models in the case of whole breast irradiation (WBI) for left-side breast irradiation with tangential fields (TF). METHODS Eight institutions set KB models, following previously shared common criteria. Plan prediction performance was tested on 16 new patients (2 pts per centre) extracting dose-volume-histogram (DVH) prediction bands of heart, ipsilateral lung, contralateral lung and breast. The inter-institutional variability was quantified by the standard deviations (SDint) of predicted DVHs and mean-dose (Dmean). The transferability of models, for the heart and the ipsilateral lung, was evaluated by the range of geometric Principal Component (PC1) applicability of a model to test patients of the other 7 institutions. RESULTS SDint of the DVH was 1.8 % and 1.6 % for the ipsilateral lung and the heart, respectively (20 %-80 % dose range); concerning Dmean, SDint was 0.9 Gy and 0.6 Gy for the ipsilateral lung and the heart, respectively (<0.2 Gy for contralateral organs). Mean predicted doses ranged between 4.3 and 5.9 Gy for the ipsilateral lung and 1.1-2.3 Gy for the heart. PC1 analysis suggested no relevant differences among models, except for one centre showing a systematic larger sparing of the heart, concomitant to a worse PTV coverage, due to high priority in sparing the left anterior descending coronary artery. CONCLUSIONS Results showed high transferability among models and low inter-institutional variability of 2% for plan prediction. These findings encourage the building of benchmark models in the case of TF-WBI.
Collapse
Affiliation(s)
- Roberta Castriconi
- Medical Physics Dept, IRCCS San Raffaele Scientific Institute, Milano, Italy.
| | - Alessia Tudda
- Medical Physics Dept, IRCCS San Raffaele Scientific Institute, Milano, Italy; Università Statale di Milano, Milano, Italy
| | - Lorenzo Placidi
- Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy
| | - Giovanna Benecchi
- Medical Physics Dept, University Hospital of Parma AOUP, Parma, Italy
| | - Elisabetta Cagni
- Medical Physics Unit, Department of Advanced Technology, Azienda USL-IRCCS di Reggio Emilia, Reggio Emilia, Italy
| | - Francesca Dusi
- Medical Physics Department, Veneto Institute of Oncology IOV-IRCCS, Padua, Italy
| | - Anna Ianiro
- IRCCS Istituto Nazionale dei Tumori Regina Elena, Rome, Italy
| | - Valeria Landoni
- IRCCS Istituto Nazionale dei Tumori Regina Elena, Rome, Italy
| | - Tiziana Malatesta
- UOC di Radioterapia Oncologica, Fatebenefratelli Isola Tiberina - Gemelli Isola, Roma, Italy
| | - Aldo Mazzilli
- Medical Physics Dept, University Hospital of Parma AOUP, Parma, Italy
| | - Guenda Meffe
- Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy
| | | | | | - Alessandro Scaggion
- Medical Physics Department, Veneto Institute of Oncology IOV-IRCCS, Padua, Italy
| | - Valeria Trojani
- Medical Physics Unit, Department of Advanced Technology, Azienda USL-IRCCS di Reggio Emilia, Reggio Emilia, Italy
| | | | - Claudio Fiorino
- Medical Physics Dept, IRCCS San Raffaele Scientific Institute, Milano, Italy
| |
Collapse
|
41
|
Cai W, Ding S, Li H, Zhou X, Dou W, Zhou L, Song T, Li Y. Automatic IMRT treatment planning through fluence prediction and plan fine-tuning for nasopharyngeal carcinoma. Radiat Oncol 2024; 19:39. [PMID: 38509540 PMCID: PMC10956235 DOI: 10.1186/s13014-024-02401-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2023] [Accepted: 01/09/2024] [Indexed: 03/22/2024] Open
Abstract
BACKGROUND At present, the implementation of intensity-modulated radiation therapy (IMRT) treatment planning for geometrically complex nasopharyngeal carcinoma (NPC) through manual trial-and-error fashion presents challenges to the improvement of planning efficiency and the obtaining of high-consistency plan quality. This paper aims to propose an automatic IMRT plan generation method through fluence prediction and further plan fine-tuning for patients with NPC and evaluates the planning efficiency and plan quality. METHODS A total of 38 patients with NPC treated with nine-beam IMRT were enrolled in this study and automatically re-planned with the proposed method. A trained deep learning model was employed to generate static field fluence maps for each patient with 3D computed tomography images and structure contours as input. Automatic IMRT treatment planning was achieved by using its generated dose with slight tightening for further plan fine-tuning. Lastly, the plan quality was compared between automatic plans and clinical plans. RESULTS The average time for automatic plan generation was less than 4 min, including fluence maps prediction with a python script and automated plan tuning with a C# script. Compared with clinical plans, automatic plans showed better conformity and homogeneity for planning target volumes (PTVs) except for the conformity of PTV-1. Meanwhile, the dosimetric metrics for most organs at risk (OARs) were ameliorated in the automatic plan, especially Dmax of the brainstem and spinal cord, and Dmean of the left and right parotid glands significantly decreased (P < 0.05). CONCLUSION We have successfully implemented an automatic IMRT plan generation method for patients with NPC. This method shows high planning efficiency and comparable or superior plan quality than clinical plans. The qualitative results before and after the plan fine-tuning indicates that further optimization using dose objectives generated by predicted fluence maps is crucial to obtain high-quality automatic plans.
Collapse
Affiliation(s)
- Wenwen Cai
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China
| | - Shouliang Ding
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, 510060, China
| | - Huali Li
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China
| | - Xuanru Zhou
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China
| | - Wen Dou
- Zhujiang Hospital, Southern Medical University, Guangzhou, 510282, China
| | - Linghong Zhou
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China
| | - Ting Song
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China.
| | - Yongbao Li
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, 510060, China.
| |
Collapse
|
42
|
Teng L, Wang B, Xu X, Zhang J, Mei L, Feng Q, Shen D. Beam-wise dose composition learning for head and neck cancer dose prediction in radiotherapy. Med Image Anal 2024; 92:103045. [PMID: 38071865 DOI: 10.1016/j.media.2023.103045] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2022] [Revised: 10/12/2023] [Accepted: 11/27/2023] [Indexed: 01/12/2024]
Abstract
Automatic and accurate dose distribution prediction plays an important role in radiotherapy plan. Although previous methods can provide promising performance, most methods did not consider beam-shaped radiation of treatment delivery in clinical practice. This leads to inaccurate prediction, especially on beam paths. To solve this problem, we propose a beam-wise dose composition learning (BDCL) method for dose prediction in the context of head and neck (H&N) radiotherapy plan. Specifically, a global dose network is first utilized to predict coarse dose values in the whole-image space. Then, we propose to generate individual beam masks to decompose the coarse dose distribution into multiple field doses, called beam voters, which are further refined by a subsequent beam dose network and reassembled to form the final dose distribution. In particular, we design an overlap consistency module to keep the similarity of high-level features in overlapping regions between different beam voters. To make the predicted dose distribution more consistent with the real radiotherapy plan, we also propose a dose-volume histogram (DVH) calibration process to facilitate feature learning in some clinically concerned regions. We further apply an edge enhancement procedure to enhance the learning of the extracted feature from the dose falloff regions. Experimental results on a public H&N cancer dataset from the AAPM OpenKBP challenge show that our method achieves superior performance over other state-of-the-art approaches by significant margins. Source code is released at https://github.com/TL9792/BDCLDosePrediction.
Collapse
Affiliation(s)
- Lin Teng
- School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China; School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China
| | - Bin Wang
- School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China
| | - Xuanang Xu
- Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, USA
| | - Jiadong Zhang
- School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China
| | - Lanzhuju Mei
- School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China
| | - Qianjin Feng
- School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China
| | - Dinggang Shen
- School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China; Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai 200230, China; Shanghai Clinical Research and Trial Center, Shanghai 201210, China.
| |
Collapse
|
43
|
Kaderka R, Dogan N, Jin W, Bossart E. Effects of model size and composition on quality of head-and-neck knowledge-based plans. J Appl Clin Med Phys 2024; 25:e14168. [PMID: 37798910 PMCID: PMC10860434 DOI: 10.1002/acm2.14168] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2023] [Revised: 08/23/2023] [Accepted: 09/15/2023] [Indexed: 10/07/2023] Open
Abstract
PURPOSE Knowledge-based planning (KBP) aims to automate and standardize treatment planning. New KBP users are faced with many questions: How much does model size matter, and are multiple models needed to accommodate specific physician preferences? In this study, six head-and-neck KBP models were trained to address these questions. METHODS The six models differed in training size and plan composition: The KBPFull (n = 203 plans), KBP101 (n = 101), KBP50 (n = 50), and KBP25 (n = 25) were trained with plans from two head-and-neck physicians. KBPA and KBPB each contained n = 101 plans from only one physician, respectively. An independent set of 39 patients treated to 6000-7000 cGy by a third physician was re-planned with all KBP models for validation. Standard head-and-neck dosimetric parameters were used to compare resulting plans. KBPFull plans were compared to the clinical plans to evaluate overall model quality. Additionally, clinical and KBPFull plans were presented to another physician for blind review. Dosimetric comparison of KBPFull against KBP101 , KBP50 , and KBP25 investigated the effect of model size. Finally, KBPA versus KBPB tested whether training KBP models on plans from one physician only influences the resulting output. Dosimetric differences were tested for significance using a paired t-test (p < 0.05). RESULTS Compared to manual plans, KBPFull significantly increased PTV Low D95% and left parotid mean dose but decreased dose cochlea, constrictors, and larynx. The physician preferred the KBPFull plan over the manual plan in 20/39 cases. Dosimetric differences between KBPFull , KBP101 , KBP50 , and KBP25 plans did not exceed 187 cGy on aggregate, except for the cochlea. Further, average differences between KBPA and KBPB were below 110 cGy. CONCLUSIONS Overall, all models were shown to produce high-quality plans. Differences between model outputs were small compared to the prescription. This indicates only small improvements when increasing model size and minimal influence of the physician when choosing treatment plans for training head-and-neck KBP models.
Collapse
Affiliation(s)
- Robert Kaderka
- Department of Radiation OncologyUniversity of Miami Miller School of MedicineMiamiFloridaUSA
| | - Nesrin Dogan
- Department of Radiation OncologyUniversity of Miami Miller School of MedicineMiamiFloridaUSA
| | - William Jin
- Department of Radiation OncologyUniversity of Miami Miller School of MedicineMiamiFloridaUSA
| | - Elizabeth Bossart
- Department of Radiation OncologyUniversity of Miami Miller School of MedicineMiamiFloridaUSA
| |
Collapse
|
44
|
Hadj Henni A, Arhoun I, Boussetta A, Daou W, Marque A. Enhancing dosimetric practices through knowledge-based predictive models: a case study on VMAT prostate irradiation. Front Oncol 2024; 14:1320002. [PMID: 38304869 PMCID: PMC10832012 DOI: 10.3389/fonc.2024.1320002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2023] [Accepted: 01/05/2024] [Indexed: 02/03/2024] Open
Abstract
Introduction Acquisition of dosimetric knowledge by radiation therapy planners is a protracted and complex process. This study delves into the impact of empirical predictive models based on the knowledge-based planning (KBP) methodology, aimed at detecting suboptimal results and homogenizing and improving existing practices for prostate cancer. Moreover, the dosimetric effect of implementing these models into routine clinical practice was also assessed. Materials and methods Based on the KBP method, we analyzed 25 prostate treatment plans performed using VMAT by expert operators, aiming to correlate dose indicators with patient geometry. The D a v g C a v ( G y ) , V 45 G y C a v ( c c ) , and V 15 G y C a v ( c c ) of the peritoneal cavity and the V 60 G y ( % ) and V 70 G y ( % ) of the rectum and bladder were linked to geometric characteristics such as the distance from the planning target volume (PTV) to the organs at risk (OAR), the volume of the OAR, or the overlap between the PTV and the OAR. In the second phase, the KBP was used in routine clinical practice in a prospective cohort of 25 patients and compared with the 41 patient plans calculated before implementing the tool. Results Using linear regression, we identified strong geometric predictive factors for the peritoneal cavity, rectum, and bladder (R 2 > 0.8), with an average prescribed dose of 97.8%, covering 95% of the target volume. The use of the model led to a significant dose reduction ( Δ ) for all evaluated OARs. This trend was most notable for Δ V 15 G y C a v = - 171.5 cc ( p = 0.003 ) . Significant reductions were also obtained in average doses to the rectum and bladder, Δ D a v g R e c t = - 2.3 G y ( p = 0.040 ) , and Δ D a v g V e s s = - 3.3 G y ( p = 0.039 ) respectively. Based on this model, we reduced the number of plans with OAR constraints above the clinical recommendations from 19% to 8%. Conclusions The KBP methodology established a robust and personalized predictive model for dose estimation to organs at risk in prostate cancer. Implementing the model resulted in improved sparing of these organs. Notably, it yields a solid foundation for harmonizing dosimetric practices, alerting us to suboptimal results, and improving our knowledge.
Collapse
Affiliation(s)
- Ahmed Hadj Henni
- Radiation Oncology Department, Centre Frederic Joliot, Rouen, France
| | - Ilias Arhoun
- Radiation Oncology Department, Centre Frederic Joliot, Rouen, France
| | | | - Walid Daou
- Mohammed VI Polytechnic University, Ben Guerir, Morocco
| | - Alexandre Marque
- Radiation Oncology Department, Centre Frederic Joliot, Rouen, France
- Oncology Department, Clinique Saint Hilaire, Rouen, France
| |
Collapse
|
45
|
Gao Y, Chang CW, Pan S, Peng J, Ma C, Patel P, Roper J, Zhou J, Yang X. Deep learning-based synthetic dose-weighted LET map generation for intensity modulated proton therapy. Phys Med Biol 2024; 69:025004. [PMID: 38091613 PMCID: PMC10767225 DOI: 10.1088/1361-6560/ad154b] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Revised: 12/02/2023] [Accepted: 12/13/2023] [Indexed: 01/06/2024]
Abstract
The advantage of proton therapy as compared to photon therapy stems from the Bragg peak effect, which allows protons to deposit most of their energy directly at the tumor while sparing healthy tissue. However, even with such benefits, proton therapy does present certain challenges. The biological effectiveness differences between protons and photons are not fully incorporated into clinical treatment planning processes. In current clinical practice, the relative biological effectiveness (RBE) between protons and photons is set as constant 1.1. Numerous studies have suggested that the RBE of protons can exhibit significant variability. Given these findings, there is a substantial interest in refining proton therapy treatment planning to better account for the variable RBE. Dose-average linear energy transfer (LETd) is a key physical parameter for evaluating the RBE of proton therapy and aids in optimizing proton treatment plans. Calculating precise LETddistributions necessitates the use of intricate physical models and the execution of specialized Monte-Carlo simulation software, which is a computationally intensive and time-consuming progress. In response to these challenges, we propose a deep learning based framework designed to predict the LETddistribution map using the dose distribution map. This approach aims to simplify the process and increase the speed of LETdmap generation in clinical settings. The proposed CycleGAN model has demonstrated superior performance over other GAN-based models. The mean absolute error (MAE), peak signal-to-noise ratio and normalized cross correlation of the LETdmaps generated by the proposed method are 0.096 ± 0.019 keVμm-1, 24.203 ± 2.683 dB, and 0.997 ± 0.002, respectively. The MAE of the proposed method in the clinical target volume, bladder, and rectum are 0.193 ± 0.103, 0.277 ± 0.112, and 0.211 ± 0.086 keVμm-1, respectively. The proposed framework has demonstrated the feasibility of generating synthetic LETdmaps from dose maps and has the potential to improve proton therapy planning by providing accurate LETdinformation.
Collapse
Affiliation(s)
- Yuan Gao
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, United States of America
| | - Chih-Wei Chang
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, United States of America
| | - Shaoyan Pan
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, United States of America
- Department of Biomedical Informatics, Emory University, Atlanta, GA, United States of America
| | - Junbo Peng
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, United States of America
| | - Chaoqiong Ma
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, United States of America
| | - Pretesh Patel
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, United States of America
| | - Justin Roper
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, United States of America
| | - Jun Zhou
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, United States of America
| | - Xiaofeng Yang
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, United States of America
- Department of Biomedical Informatics, Emory University, Atlanta, GA, United States of America
- Department of Nuclear & Radiological Engineering and Medical Physics, Georgia Institute of Technology, Atlanta, GA, United States of America
| |
Collapse
|
46
|
Shen Y, Tang X, Lin S, Jin X, Ding J, Shao M. Automatic dose prediction using deep learning and plan optimization with finite-element control for intensity modulated radiation therapy. Med Phys 2024; 51:545-555. [PMID: 37748133 DOI: 10.1002/mp.16743] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2023] [Revised: 07/21/2023] [Accepted: 08/26/2023] [Indexed: 09/27/2023] Open
Abstract
BACKGROUND Automatic solutions for generating radiotherapy treatment plans using deep learning (DL) have been investigated by mimicking the voxel's dose. However, plan optimization using voxel-dose features has not been extensively studied. PURPOSE This study aims to investigate the efficiency of a direct optimization strategy with finite elements (FEs) after DL dose prediction for automatic intensity-modulated radiation therapy (IMRT) treatment planning. METHODS A double-UNet DL model was adapted for 220 cervical cancer patients (200 for training and 20 for testing), who underwent IMRT between 2016 and 2020 at our clinic. The model inputs were computed tomography (CT) slices, organs at risk (OARs), and planning target volumes (PTVs), and the outputs were dose distributions of uniformly generated high-dose region-controlled plans. The FEs were discretized into equal intervals of the dose prediction value within the [OARs avoid PTV(O-P)] and [body avoids OARs & PTV(B-OP)] regions in the test cohort and used to define the objectives for IMRT plan optimization. The plans were optimized using a two-step process. In the beginning, the plans of two extra cases with and without low-dose region control were compared to pursue robust and optimal dose adjustment degree pattern of FEs. In the first step, the mean dose of O-P FEs were constrained to differing degrees according to the pattern. The further the FEs from the PTV, the tighter the constraints. In the second step, the mean dose of O-P FEs from first step were constrained again but weakly and the dose of the B-OP FEs from dose prediction and PTV were tightly regulated. The dosimetric parameters of the OARs and PTV were evaluated and compared using an interstep approach. In another 10 cases, the plans optimized via the aforementioned steps (method 1) were compared with those directly generated by the double-UNet dose prediction model trained by low and high region-controlled plans (method 2). RESULTS The mean differences in dose metrics between the UNet-predicted dose and the clinical plans were: 0.47 Gy for bladder D50% ; 0.62 Gy for rectum D50% ; 0% for small intestine V30Gy ; 1% for small intestine V40Gy ; 4% for left femoral head V30Gy ; and 6% for right femoral head V30Gy . The reductions in mean dose (p < 0.001) after FE-based optimization were: 4.0, 1.9, 2.8, 5.9, and 5.7 Gy for the bladder, rectum, small intestine, left femoral head, and right femoral head, respectively, with flat PTV homogeneity and conformity. Method 1 plans produced lower mean doses than those of method 2 for the bladder (0.7 Gy), rectum (1.0 Gy), and small intestine (0.6 Gy), while maintaining PTV homogeneity and conformity. CONCLUSION FE-based direct optimization produced lower OAR doses and adequate PTV doses after DL prediction. This solution offers rapid and automatic plan optimization without manual adjustment, particularly in low-dose regions.
Collapse
Affiliation(s)
- Yichao Shen
- Department of Radiation Oncology, Taizhou Hospital, Taizhou, Zhejiang, People's Republic of China
| | - Xingni Tang
- Department of Radiation Oncology, Taizhou Hospital, Taizhou, Zhejiang, People's Republic of China
| | - Sara Lin
- Petrone associates, Staten Island, New York, USA
| | - Xiance Jin
- Radiotherapy Center Department, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, People's Republic of China
| | - Jiapei Ding
- Department of Radiation Oncology, Taizhou Hospital, Taizhou, Zhejiang, People's Republic of China
| | - Minghai Shao
- Department of Radiation Oncology, Taizhou Hospital, Taizhou, Zhejiang, People's Republic of China
| |
Collapse
|
47
|
Roberfroid B, Barragán-Montero AM, Dechambre D, Sterpin E, Lee JA, Geets X. Comparison of Ethos template-based planning and AI-based dose prediction: General performance, patient optimality, and limitations. Phys Med 2023; 116:103178. [PMID: 38000099 DOI: 10.1016/j.ejmp.2023.103178] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Revised: 10/19/2023] [Accepted: 11/16/2023] [Indexed: 11/26/2023] Open
Abstract
PURPOSE Ethos proposes a template-based automatic dose planning (Etb) for online adaptive radiotherapy. This study evaluates the general performance of Etb for prostate cancer, as well as the ability to generate patient-optimal plans, by comparing it with another state-of-the-art automatic planning method, i.e., deep learning dose prediction followed by dose mimicking (DP + DM). MATERIALS General performances and capability to produce patient-optimal plan were investigated through two studies: Study-S1 generated plans for 45 patients using our initial Ethos clinical goals template (EG_init), and compared them to manually generated plans (MG). For study-S2, 10 patients which showed poor performances at study-S1 were selected. S2 compared the quality of plans generated with four different methods: 1) Ethos initial template (EG_init_selected), 2) Ethos updated template-based on S1 results (EG_upd_selected), 3) DP + DM, and 4) MG plans. RESULTS EG_init plans showed satisfactory performance for dose level above 50 Gy: reported mean metrics differences (EG_init minus MG) never exceeded 0.6 %. However, lower dose levels showed loosely optimized metrics, mean differences for V30Gy to rectum and V20Gy to anal canal were of 6.6 % and 13.0 %. EG_init_selected showed amplified differences in V30Gy to rectum and V20Gy to anal canal: 8.5 % and 16.9 %, respectively. These dropped to 5.7 % and 11.5 % for EG_upd_selected plans but strongly increased V60Gy to rectum for 2 patients. DP + DM plans achieved differences of 3.4 % and 4.6 % without compromising any V60Gy. CONCLUSION General performances of Etb were satisfactory. However, optimizing with template of goals might be limiting for some complex cases. Over our test patients, DP + DM outperformed the Etb approach.
Collapse
Affiliation(s)
- Benjamin Roberfroid
- Université catholique de Louvain - Center of Molecular Imaging, Radiotherapy and Oncology (MIRO), Brussels, Belgium.
| | - Ana M Barragán-Montero
- Université catholique de Louvain - Center of Molecular Imaging, Radiotherapy and Oncology (MIRO), Brussels, Belgium
| | - David Dechambre
- Cliniques universitaires Saint-Luc, Department of Radiation Oncology, Brussels, Belgium
| | - Edmond Sterpin
- Université catholique de Louvain - Center of Molecular Imaging, Radiotherapy and Oncology (MIRO), Brussels, Belgium; Particle Therapy Interuniversity Center Leuven - PARTICLE, Leuven, Belgium; KU Leuven - Department of Oncology, Laboratory of Experimental Radiotherapy, Leuven, Belgium
| | - John A Lee
- Université catholique de Louvain - Center of Molecular Imaging, Radiotherapy and Oncology (MIRO), Brussels, Belgium
| | - Xavier Geets
- Université catholique de Louvain - Center of Molecular Imaging, Radiotherapy and Oncology (MIRO), Brussels, Belgium; Cliniques universitaires Saint-Luc, Department of Radiation Oncology, Brussels, Belgium
| |
Collapse
|
48
|
Pogue JA, Cardenas CE, Harms J, Soike MH, Kole AJ, Schneider CS, Veale C, Popple R, Belliveau JG, McDonald AM, Stanley DN. Benchmarking Automated Machine Learning-Enhanced Planning With Ethos Against Manual and Knowledge-Based Planning for Locally Advanced Lung Cancer. Adv Radiat Oncol 2023; 8:101292. [PMID: 37457825 PMCID: PMC10344691 DOI: 10.1016/j.adro.2023.101292] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2023] [Accepted: 06/02/2023] [Indexed: 07/18/2023] Open
Abstract
Purpose Currently, there is insufficient guidance for standard fractionation lung planning using the Varian Ethos adaptive treatment planning system and its unique intelligent optimization engine. Here, we address this gap in knowledge by developing a methodology to automatically generate high-quality Ethos treatment plans for locally advanced lung cancer. Methods and Materials Fifty patients previously treated with manually generated Eclipse plans for inoperable stage IIIA-IIIC non-small cell lung cancer were included in this institutional review board-approved retrospective study. Fifteen patient plans were used to iteratively optimize a planning template for the Daily Adaptive vs Non-Adaptive External Beam Radiation Therapy With Concurrent Chemotherapy for Locally Advanced Non-Small Cell Lung Cancer: A Prospective Randomized Trial of an Individualized Approach for Toxicity Reduction (ARTIA-Lung); the remaining 35 patients were automatically replanned without intervention. Ethos plan quality was benchmarked against clinical plans and reoptimized knowledge-based RapidPlan (RP) plans, then judged using standard dose-volume histogram metrics, adherence to clinical trial objectives, and qualitative review. Results Given equal prescription target coverage, Ethos-generated plans showed improved primary and nodal planning target volume V95% coverage (P < .001) and reduced lung gross tumor volume V5 Gy and esophagus D0.03 cc metrics (P ≤ .003) but increased mean esophagus and brachial plexus D0.03 cc metrics (P < .001) compared with RP plans. Eighty percent, 49%, and 51% of Ethos, clinical, and RP plans, respectively, were "per protocol" or met "variation acceptable" ARTIA-Lung planning metrics. Three radiation oncologists qualitatively scored Ethos plans, and 78% of plans were clinically acceptable to all reviewing physicians, with no plans receiving scores requiring major changes. Conclusions A standard Ethos template produced lung radiation therapy plans with similar quality to RP plans, elucidating a viable approach for automated plan generation in the Ethos adaptive workspace.
Collapse
Affiliation(s)
- Joel A. Pogue
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
| | - Carlos E. Cardenas
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
| | - Joseph Harms
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
| | - Michael H. Soike
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
| | - Adam J. Kole
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
| | - Craig S. Schneider
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
| | - Christopher Veale
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
| | - Richard Popple
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
| | - Jean-Guy Belliveau
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
| | - Andrew M. McDonald
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
- University of Alabama at Birmingham Institute for Cancer Outcomes and Survivorship, Birmingham, Alabama
| | - Dennis N. Stanley
- Department of Radiation Oncology, University of Alabama at Birmingham, Birmingham, Alabama
| |
Collapse
|
49
|
Schlachter M, Peters S, Camenisch D, Putora PM, Bühler K. Exploration of overlap volumes for radiotherapy plan evaluation with the aim of healthy tissue sparing. Comput Biol Med 2023; 166:107523. [PMID: 37778212 DOI: 10.1016/j.compbiomed.2023.107523] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2023] [Revised: 08/17/2023] [Accepted: 09/19/2023] [Indexed: 10/03/2023]
Abstract
PURPOSE Development of a novel interactive visualization approach for the exploration of radiotherapy treatment plans with a focus on overlap volumes with the aim of healthy tissue sparing. METHODS We propose a visualization approach to include overlap volumes in the radiotherapy treatment plan evaluation process. Quantitative properties can be interactively explored to identify critical regions and used to steer the visualization for a detailed inspection of candidates. We evaluated our approach with a user study covering the individual visualizations and their interactions regarding helpfulness, comprehensibility, intuitiveness, decision-making and speed. RESULTS A user study with three domain experts was conducted using our software and evaluating five data sets each representing a different type of cancer and location by performing a set of tasks and filling out a questionnaire. The results show that the visualizations and interactions help to identify and evaluate overlap volumes according to their physical and dose properties. Furthermore, the task of finding dose hot spots can also benefit from our approach. CONCLUSIONS The results indicate the potential to enhance the current treatment plan evaluation process in terms of healthy tissue sparing.
Collapse
Affiliation(s)
- Matthias Schlachter
- VRVis Zentrum für Virtual Reality und Visualisierung Forschungs-GmbH, Vienna, Austria.
| | - Samuel Peters
- Department of Radiation Oncology, Kantonsspital St. Gallen, St. Gallen, Switzerland
| | - Daniel Camenisch
- Department of Radiation Oncology, Kantonsspital St. Gallen, St. Gallen, Switzerland
| | - Paul Martin Putora
- Department of Radiation Oncology, Kantonsspital St. Gallen, St. Gallen, Switzerland; Department of Radiation Oncology, University of Bern, Bern, Switzerland
| | - Katja Bühler
- VRVis Zentrum für Virtual Reality und Visualisierung Forschungs-GmbH, Vienna, Austria
| |
Collapse
|
50
|
Harms J, Pogue JA, Cardenas CE, Stanley DN, Cardan R, Popple R. Automated evaluation for rapid implementation of knowledge-based radiotherapy planning models. J Appl Clin Med Phys 2023; 24:e14152. [PMID: 37703545 PMCID: PMC10562024 DOI: 10.1002/acm2.14152] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2023] [Accepted: 08/29/2023] [Indexed: 09/15/2023] Open
Abstract
PURPOSE Knowledge-based planning (KBP) offers the ability to predict dose-volume metrics based on information extracted from previous plans, reducing plan variability and improving plan quality. As clinical integration of KBP is increasing there is a growing need for quantitative evaluation of KBP models. A .NET-based application, RapidCompare, was created for automated plan creation and analysis of Varian RapidPlan models. METHODS RapidCompare was designed to read calculation parameters and a list of reference plans. The tool copies the reference plan field geometry and structure set, applies the RapidPlan model, optimizes the KBP plan, and generates data for quantitative evaluation of dose-volume metrics. A cohort of 85 patients, divided into training (50), testing (10), and validation (25) groups, was used to demonstrate the utility of RapidCompare. After training and tuning, the KBP model was paired with three different optimization templates to compare various planning strategies in the validation cohort. All templates used the same set of constraints for the planning target volume (PTV). For organs-at-risk, the optimization template provided constraints using the whole dose-volume histogram (DVH), fixed-dose/volume points, or generalized equivalent uniform dose (gEUD). The resulting plans from each optimization approach were compared using DVH metrics. RESULTS RapidCompare allowed for the automated generation of 75 total plans for comparison with limited manual intervention. In comparing optimization techniques, the Dose/Volume and Lines optimization templates generated plans with similar DVH metrics, with a slight preference for the Lines technique with reductions in heart V30Gy and spinal cord max dose. The gEUD model produced high target heterogeneity. CONCLUSION Automated evaluation allowed for the exploration of multiple optimization templates in a larger validation cohort than would have been feasible using a manual approach. A final KBP model using line optimization objectives produced the highest quality plans without human intervention.
Collapse
Affiliation(s)
- Joseph Harms
- Department of Radiation OncologyUniversity of Alabama at BirminghamBirminghamUSA
| | - Joel A. Pogue
- Department of Radiation OncologyUniversity of Alabama at BirminghamBirminghamUSA
| | - Carlos E. Cardenas
- Department of Radiation OncologyUniversity of Alabama at BirminghamBirminghamUSA
| | - Dennis N. Stanley
- Department of Radiation OncologyUniversity of Alabama at BirminghamBirminghamUSA
| | - Rex Cardan
- Department of Radiation OncologyUniversity of Alabama at BirminghamBirminghamUSA
| | - Richard Popple
- Department of Radiation OncologyUniversity of Alabama at BirminghamBirminghamUSA
| |
Collapse
|