• Adaptive radiotherapy
• Case report
• Cervical cancer
• Chemoradiotherapy

• CBCT
• RapidPlan
• adaptive radiotherapy
• knowledge‐based planning
• prostate radiotherapy

• Humans
• Radiotherapy Planning, Computer-Assisted/methods
• Male
• Radiotherapy, Intensity-Modulated/methods
• Cone-Beam Computed Tomography/methods
• Radiotherapy Dosage
• Prostatic Neoplasms/radiotherapy
• Prostatic Neoplasms/diagnostic imaging
• Organs at Risk/radiation effects
• Particle Accelerators/instrumentation
• Retrospective Studies
• Knowledge Bases
• Image Processing, Computer-Assisted/methods
• Algorithms
• Pelvis/diagnostic imaging

• Ethos
• MR-guided radiotherapy
• online adaptive radiotherapy

• Artificial Intelligence
• Automated treatment planning
• Deep learning dose prediction
• Online Adaptive Radiotherapy (oART)

• Male
• Humans
• Radiotherapy Dosage
• Radiotherapy Planning, Computer-Assisted/methods
• Rectum
• Pelvis
• Anal Canal
• Radiotherapy, Intensity-Modulated/methods
• Organs at Risk

• Head and neck cancer
• online adaptive radiotherapy
• treatment planning

• Humans
• Radiotherapy Dosage
• Radiotherapy Planning, Computer-Assisted
• Retrospective Studies
• Spiral Cone-Beam Computed Tomography
• Organs at Risk
• Radiotherapy, Intensity-Modulated

• Varian Medical Systems, Palo Alto, CA

• Adaptive radiotherapy (ART)
• Cone-beam computed tomography (CBCT)
• Ethos™

• Humans
• Artificial Intelligence
• Radiation Oncology
• Cone-Beam Computed Tomography
• Machine Learning
• Motion
• Radiation Injuries

• IMPT
• IMRT
• online adaptive radiation therapy
• online adaptive treatment planning

• Humans
• Radiotherapy, Intensity-Modulated/methods
• Radiotherapy Planning, Computer-Assisted/methods
• Radiotherapy Dosage
• Artificial Intelligence

• R01 CA266275 NCI NIH HHS
• R01 CA266803 NCI NIH HHS

• MR-linac
• PSQA
• adaptive radiotherapy
• dose delivery accuracy

• gynecologic cancer
• online adaptive radiotherapy
• radiation oncology

• Humans
• Female
• Organs at Risk/pathology
• Artificial Intelligence
• Radiotherapy, Image-Guided/methods
• Urinary Bladder Neoplasms
• Radiotherapy Dosage
• Radiotherapy Planning, Computer-Assisted/methods

• MR-linac
• MRI-guided adaptive radiation therapy
• Online adaptive replanning
• Pancreatic cancer
• Wavelets

• Humans
• Radiotherapy Planning, Computer-Assisted/methods
• Bayes Theorem
• Particle Accelerators
• Magnetic Resonance Imaging/methods
• Pancreatic Neoplasms/diagnostic imaging
• Pancreatic Neoplasms/radiotherapy

• R01 CA247960 NCI NIH HHS

Adaptive radiotherapy has the potential to reduce margins, improve target coverage, and decrease toxicity to organs at risk (OARs) by optimizing radiation delivery to daily anatomic changes. Salvage for locally recurrent prostate cancer after definitive radiation remains a challenging clinical scenario given the risks to normal tissue in a setting of re-irradiation. Here, we present a case series of five patients with locally recurrent prostate cancer treated with an adaptive online linear accelerator or a 3-T MR-based linear accelerator to demonstrate excellent target coverage. All patients completed the planned treatment course with acceptable acute toxicities but a short follow-up time does not inform subacute/late toxicities.

Hybrid magnetic resonance (MR)-Linac systems have recently been introduced into clinical practice. The systems allow online adaption of the treatment plan with the aim of compensating for interfractional anatomical changes. The aim of this study was to evaluate the dose volume histogram (DVH)-based dosimetric benefits of online adaptive MR-guided radiotherapy (oMRgRT) across different tumor entities and to investigate which subgroup of plans improved the most from adaption.

Fifty patients treated with oMRgRT for five different tumor entities (liver, lung, multiple abdominal lymph nodes, pancreas, and prostate) were included in this retrospective analysis. Various target volume (gross tumor volume GTV, clinical target volume CTV, and planning target volume PTV) and organs at risk (OAR) related DVH parameters were compared between the dose distributions before and after plan adaption.

All subgroups clearly benefited from online plan adaption in terms of improved PTV coverage. For the liver, lung and abdominal lymph nodes cases, a consistent improvement in GTV coverage was found, while many fractions of the prostate subgroup showed acceptable CTV coverage even before plan adaption. The largest median improvements in GTV near-minimum dose (D_98%) were found for the liver (6.3%, p < 0.001), lung (3.9%, p < 0.001), and abdominal lymph nodes (6.8%, p < 0.001) subgroups. Regarding OAR sparing, the largest median OAR dose reduction during plan adaption was found for the pancreas subgroup (-87.0%). However, in the pancreas subgroup an optimal GTV coverage was not always achieved because sparing of OARs was prioritized.

With online plan adaptation, it was possible to achieve significant improvements in target volume coverage and OAR sparing for various tumor entities and account for interfractional anatomical changes.

• 0.35 Tesla MR Guidance
• 1.5 Tesla MR Guidance
• RT adaption
• Unity
• ViewRay
• adaptive image guidance
• adaptive radiation therapy
• magnetic resonance (MR)-guided radiation
• personalized radiation therapy

• History, 20th Century
• History, 21st Century
• Humans
• Magnetic Resonance Imaging, Interventional/history
• Magnetic Resonance Imaging, Interventional/instrumentation
• Magnetic Resonance Imaging, Interventional/methods
• Magnetic Resonance Imaging, Interventional/trends
• Neoplasms/diagnostic imaging
• Neoplasms/radiotherapy
• Particle Accelerators
• Radiation Oncology/history
• Radiation Oncology/instrumentation
• Radiation Oncology/methods
• Radiation Oncology/trends
• Radiotherapy Planning, Computer-Assisted/history
• Radiotherapy Planning, Computer-Assisted/instrumentation
• Radiotherapy Planning, Computer-Assisted/methods
• Radiotherapy Planning, Computer-Assisted/trends

• OT2 OD026675 NIH HHS
• P30 CA016672 NCI NIH HHS
• F31 DE029093 NIDCR NIH HHS
• R01 DE025248 NIDCR NIH HHS
• R01 CA214825 NCI NIH HHS
• R01 HL153720 NHLBI NIH HHS
• R01 CA225190 NCI NIH HHS
• 28284 Cancer Research UK
• R21 CA256144 NCI NIH HHS
• R01 CA257814 NCI NIH HHS
• R01 DE028290 NIDCR NIH HHS
• TL1 TR003169 NCATS NIH HHS
• R21 DE031082 NIDCR NIH HHS
• R25 EB025787 NIBIB NIH HHS
• KL2TR001438 NIH HHS
• R01 CA218148 NCI NIH HHS
• R43 CA254559 NCI NIH HHS
• R01 CA258827 NCI NIH HHS
• R01 CA204189 NCI NIH HHS
• KL2 TR001438 NCATS NIH HHS

The Varian Ethos system allows for online adaptive treatments through the utilization of artificial intelligence (AI) and deformable image registration which automates large parts of the anatomical contouring and plan optimization process. In this study, treatments of intact prostate and prostate bed, with and without nodes, were simulated for 182 online adaptive fractions, and then a further 184 clinical fractions were delivered on the Ethos system. Frequency and magnitude of contour edits were recorded, as well as a range of plan quality metrics. From the fractions analyzed, 11% of AI generated contours, known as influencer contours, required no change, and 81% required minor edits in any given fraction. The frequency of target and noninfluencer organs at risk (OAR) contour editing varied substantially between different targets and noninfluencer OARs, although across all targets 72% of cases required no edits. The adaptive plan was the preference in 95% of fractions. The adaptive plan met more goals than the scheduled plan in 78% of fractions, while in 15% of fractions the number of goals met was the same. The online adaptive recontouring and replanning process was carried out in 19 min on average. Significant improvements in dosimetry are possible with the Ethos online adaptive system in prostate radiotherapy.

• adaptive therapy
• deformable registration
• machine learning

• CBCT
• CT-on-rails
• Monte Carlo
• adaptive proton therapy
• head-and-neck cancers
• positioning uncertainties

• Adaptive radiotherapy
• Adaptive treatment planning
• Prostate stereotactic body radiotherapy
• Synthetic cone-beam CT

• Aged
• Aged, 80 and over
• Follow-Up Studies
• Humans
• Image Processing, Computer-Assisted/methods
• Male
• Middle Aged
• Organs at Risk/radiation effects
• Prognosis
• Prostatic Neoplasms/diagnostic imaging
• Prostatic Neoplasms/pathology
• Prostatic Neoplasms/surgery
• Radiosurgery/methods
• Radiotherapy Dosage
• Radiotherapy Planning, Computer-Assisted/methods
• Radiotherapy, Intensity-Modulated/methods
• Retrospective Studies
• Surgery, Computer-Assisted/methods
• Tomography, X-Ray Computed/methods

• Medizinische Fakultät Mannheim der Universität Heidelberg (8990)

Studies have demonstrated the potential of online adaptive radiotherapy (oART). However, routine use has been limited due to resource demanding solutions. This study reports on experiences with oART in the pelvic region using a novel cone-beam computed tomography (CBCT)-based, artificial intelligence (AI)-driven solution.

Automated pre-treatment planning for thirty-nine pelvic cases (bladder, rectum, anal, and prostate), and one hundred oART simulations were conducted in a pre-clinical release of Ethos (Varian Medical Systems, Palo Alto, CA). Plan quality, AI-segmentation accuracy, oART feasibility and an integrated calculation-based quality assurance solution were evaluated. Experiences from the first five clinical oART patients (three bladder, one rectum and one sarcoma) are reported.

Auto-generated pre-treatment plans demonstrated similar planning target volume (PTV) coverage and organs at risk doses, compared to institution reference. More than 75% of AI-segmentations during simulated oART required none or minor editing and the adapted plan was superior in 88% of cases. Limitations in AI-segmentation correlated to cases where AI model training was lacking. The five first treated patients complied well with the median adaptive procedure duration of 17.6 min (from CBCT acceptance to treatment delivery start). The treated bladder patients demonstrated a 42% median primary PTV reduction, indicating a 24%-30% reduction in V_45Gy to the bowel cavity, compared to non-ART.

A novel commercial oART solution was demonstrated feasible for various pelvic sites. Clinically acceptable AI-segmentation and auto-planning enabled adaptation within reasonable timeslots. Possibilities for reduced PTVs observed for bladder cancer indicated potential for toxicity reductions.

• Artificial Intelligence
• Automated treatment planning
• Bladder cancer
• CBCT image-guided radiotherapy
• Online Adaptive Radiotherapy (oART)
• Workflow

• Humans
• Male
• Internet
• Organs at Risk
• Radiotherapy, Image-Guided/methods

To assess the performance and limitations of contour propagation with three commercial deformable image registration (DIR) algorithms using fractional scans of CT‐on‐rails (CTOR) and Cone Beam CT (CBCT) in image guided prostate therapy patients treated with IMRT/VMAT.

Twenty prostate cancer patients treated with IMRT/VMAT were selected for analysis. A total of 453 fractions across those patients were analyzed. Image data were imported into MIM (MIM Software, Inc., Cleveland, OH) and three DIR algorithms (DIR Profile, normalized intensity‐based (NIB) and shadowed NIB DIR algorithms) were applied to deformably register each fraction with the planning CT. Manually drawn contours of bladder and rectum were utilized for comparison against the DIR propagated contours in each fraction. Four metrics were utilized in the evaluation of contour similarity, the Hausdorff Distance (HD), Mean Distance to Agreement (MDA), Dice Similarity Coefficient (DSC), and Jaccard indices. A subfactor analysis was performed per modality (CTOR vs. CBCT) and time (fraction). Point estimates and 95% confidence intervals were assessed via a Linear Mixed Effect model for the contour similarity metrics.

No statistically significant differences were observed between the DIR Profile and NIB algorithms. However, statistically significant differences were observed between the shadowed NIB and NIB algorithms for some of the DIR evaluation metrics. The Hausdorff Distance calculation showed the NIB propagated contours vs. shadowed NIB propagated contours against the manual contours were 14.82 mm vs. 8.34 mm for bladder and 15.87 mm vs. 11 mm for rectum, respectively. Similarly, the Mean Distance to Agreement calculation comparing the NIB propagated contours vs. shadowed NIB propagated contours against the manual contours were 2.43 mm vs. 0.98 mm for bladder and 2.57 mm vs. 1.00 mm for rectum, respectively. The Dice Similarity Coefficients comparing the NIB propagated contours and shadowed NIB propagated contours against the manual contours were 0.844 against 0.936 for bladder and 0.772 against 0.907 for rectum, respectively. The Jaccard indices comparing the NIB propagated contours and shadowed NIB propagated contours against the manual contours were 0.749 against 0.884 for bladder and 0.637 against 0.831 for rectum, respectively. The shadowed NIB DIR, which showed the closest agreement with the manual contours performed significantly better than the DIR Profile in all the comparisons. The OAR with the greatest agreement varied substantially across patients and image guided radiation therapy (IGRT) modality. Intra‐patient variability of contour metric evaluation was insignificant across all the DIR algorithms. Statistical significance at α = 0.05 was observed for manual vs. deformably propagated contours for bladder for all the metrics except Hausdorff Distance (P = 0.01 for MDA, P = 0.02 for DSC, P = 0.01 for Jaccard), whereas the corresponding values for rectum were: P = 0.03 for HD, P = 0.01 for MDA, P < 0.01 for DSC, P < 0.01 for Jaccard. The performance of the different metrics varied slightly across the fractions of each patient, which indicates that weekly contour propagation models provide a reasonable approximation of the daily contour propagation models.

The high variance of Hausdorff Distance across all automated methods for bladder indicates widely variable agreement across fractions for all patients. Lower variance across all modalities, methods, and metrics were observed for rectum. The shadowed NIB propagated contours were substantially more similar to the manual contours than the DIR Profile or NIB contours for both the CTOR and CBCT imaging modalities. The relationship of each algorithm to similarity with manual contours is consistent across all observed metrics and organs. Screening of image guidance for substantial differences in bladder and rectal filling compared with the planning CT reference could aid in identifying fractions for which automated DIR would prove insufficient.

• IMRT
• VMAT
• cone beam CT
• deformable image registration
• prostate cancer

• Focal boost
• Prostatic neoplasms
• Radiotherapy
• Stereotactic body radiotherapy

• Humans
• Male
• Consensus
• Prospective Studies
• Prostatic Neoplasms/radiotherapy
• Radiosurgery/methods
• Radiosurgery/standards
• Radiotherapy Dosage
• Retrospective Studies

• Cervical cancer
• intensity-modulated proton therapy (IMPT)
• online treatment planning
• online-adaptive proton therapy
• plan-library

• Humans
• Neoplasms/diagnostic imaging
• Neoplasms/radiotherapy
• Organ Sparing Treatments
• Organs at Risk
• Patient Positioning
• Radiation Oncology/methods
• Radiosurgery/methods
• Radiotherapy Planning, Computer-Assisted/methods
• Radiotherapy, Image-Guided/methods
• Radiotherapy, Intensity-Modulated/methods

• adaptive radiation therapy
• online replanning
• parallel operation in radiation therapy
• radiation therapy planning

The aim of this study was to evaluate a dual marker‐based and soft‐tissue based image guidance for inter‐fractional corrections in stereotactic body radiotherapy (SBRT) of prostate cancer.

We reviewed 18 patients treated with SBRT for prostate cancer. An endorectal balloon was inserted at simulation and each treatment. Planning margins were 3 mm/0 mm posteriorly. Prior to each treatment, a dual image guidance protocol was applied to align three makers using stereoscopic x ray images and then to the soft tissue using kilo‐voltage cone beam CT (kV‐CBCT). After treatment, prostate (CTV), rectal wall, and bladder were delineated on each kV‐CBCT, and delivered dose was recalculated. Dosimetric endpoints were analyzed, including V_{36.25 Gy} for prostate, and D_{0.03 cc} for bladder and rectal wall.

Following initial marker alignment, additional translational shifts were applied to 22 of 84 fractions after kV‐CBCT. Among the 22 fractions, ten fractions exceeded 3 mm shifts in any direction, including one in the left‐right direction, four in the superior‐inferior direction, and five in the anterior‐posterior direction. With and without the additional kV‐CBCT shifts, the average V_{36.25 Gy} of the prostate for the 22 fractions was 97.6 ± 2.6% with the kV x ray image alone, and was 98.1 ± 2.4% after applying the additional kV‐CBCT shifts. The improvement was borderline statistical significance using Wilcoxon signed‐rank test (P = 0.007). D_{0.03 cc} was 45.8 ± 6.3 Gy vs. 45.1 ± 4.9 Gy for the rectal wall; and 49.5 ± 8.6 Gy vs. 49.3 ± 7.9 Gy for the bladder before and after applying kV‐CBCT shifts.

Marker‐based alignment alone is not sufficient. Additional adjustments are needed for some patients based kV‐CBCT.

• SBRT
• endorectal balloon
• kV-CBCT
• prostate

• Algorithms
• Body Weight
• Gamma Rays
• Humans
• Male
• Models, Theoretical
• Organs at Risk
• Photons
• Prostatic Neoplasms/diagnostic imaging
• Prostatic Neoplasms/radiotherapy
• Radiometry/methods
• Radiotherapy Dosage
• Radiotherapy Planning, Computer-Assisted/methods
• Radiotherapy, Intensity-Modulated/methods
• Tomography, X-Ray Computed

• Beam scanning
• Lon beam therapy
• Organ motion

Using a MatriXX 2D ionization chamber array, we evaluated the detection sensitivity of systematically introduced MLC leaf positioning shifts to test whether the conventional IMRT QA method can be used for quality assurance of an MLC tracking algorithm. Because of finite special resolution, we first tested whether the detection sensitivity was dependent of the locations of leaf shifts and positions of ionization chambers. We then introduced the same systematic leaf shifts in two clinical intensity modulated radiotherapy plans (prostate and head and neck cancer). Our results reported differences between the measured planar doses with and without MLC shifts (errors). Independent of the locations of the leaf position shifts and positions of the detectors, for the simple rectangular fields, the MatriXX was able to detect ±2 mm MLC leaf positioning shifts with Gamma index of 3%/3 mm and ±1 mm MLC leaf position shifts with Gamma index of 2%/2 mm. For the clinical plans, measuring the fields individually, leaf positioning shifts of ±2 mm were detected using Gamma index of 3%/3 mm and a passing rate of 95%. When the fields were measured compositely, the Gamma index exhibited less sensitivity for the detection of leaf positioning shifts than when the fields were measured individually. In conclusion, if more than 2 mm MLC leaf shifts were required, the commercial detector array (MatriXX) is able to detect such MLC positioning shifts, otherwise a more sensitive quality assurance method should be used.

• Gamma index
• MatriXX
• leaf positioning shift
• multileaf collimator (MLC)
• patient-specific IMRT QA

• Adaptive
• MR-guided
• Online
• Pancreas
• Planning
• Stereotactic

• Adaptive
• IGRT
• NTCP
• prostate cancer
• radiotherapy

• automatic multiorgan segmentation
• radiotherapy treatment planning
• image segmentation
• cancer treatment

• Algorithms
• Automation
• Cluster Analysis
• Humans
• Image Processing, Computer-Assisted/methods
• Male
• Pelvis/diagnostic imaging
• Principal Component Analysis
• Prostatic Neoplasms/diagnostic imaging
• Tomography, X-Ray Computed

• R00 CA166186 NCI NIH HHS
• R01 EB016777 NIBIB NIH HHS

• Adaptive radiotherapy
• IGRT
• MR-Linac
• MRI
• Prostate

• pattern recognition
• atlas
• prostate cancer
• imrt

• Algorithms
• Anatomy, Artistic
• Atlases as Topic
• Humans
• Image Processing, Computer-Assisted/methods
• Male
• Pattern Recognition, Automated/methods
• Prostatic Neoplasms/radiotherapy
• Radiotherapy Planning, Computer-Assisted/methods
• Radiotherapy, Intensity-Modulated/methods
• Rectum/diagnostic imaging
• Retrospective Studies
• Seminal Vesicles/diagnostic imaging
• Tomography, X-Ray Computed
• Urinary Bladder/diagnostic imaging

• R21 CA161389 NCI NIH HHS
• R21CA161389 NCI NIH HHS

This study investigated a relationship between rectum diameter and prostate motion during treatment with a view to reducing planning target volume (PTV) margins for an adaptive protocol. One hundred and ninety-four cone-beam computed tomography (CBCT) images of 10 patients were used to relate rectum diameter on CBCT to prostate intrafraction displacement. A threshold rectum diameter was used to model the impact of an adaptive PTV margin on rectum and bladder dose. Potential dose escalation with a 6 mm uniform margin adaptive protocol was compared to a PTV margin of 10 mm expansion of the clinical target volume (CTV) except 6 mm posterior. Of 194 fractions, 104 had a maximum rectal diameter of ≤3.5 cm. The prostate displaced ≤4 mm in 102 of those fractions. Changing from a standard to an adaptive PTV margin reduced the volume of rectum receiving 25, 50, 60, and 70 Gy by around 12, 9, 10, and 16%, respectively and bladder by approximately 21, 27, 29, and 35%, respectively. An average dose escalation of 4.2 Gy may be possible with an adaptive prostate radiotherapy protocol. In conclusion, a relationship between the prostate motion and the diameter of the rectum on CBCT potentially could enable daily adaptive radiotherapy which can be implemented from the first fraction.

• Cancer
• image-guided
• prostate
• radiotherapy
• rectum