|
1
|
Lin A, Song L, Wang Y, Yan K, Tang H. Future prospects of deep learning in esophageal cancer diagnosis and clinical decision support (Review). Oncol Lett 2025; 29:293. [PMID: 40271007 PMCID: PMC12016012 DOI: 10.3892/ol.2025.15039] [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: 11/26/2024] [Accepted: 03/18/2025] [Indexed: 04/25/2025] Open
Abstract
Esophageal cancer (EC) is one of the leading causes of cancer-related mortality worldwide, still faces significant challenges in early diagnosis and prognosis. Early EC lesions often present subtle symptoms and current diagnostic methods are limited in accuracy due to tumor heterogeneity, lesion morphology and variable image quality. These limitations are particularly prominent in the early detection of precancerous lesions such as Barrett's esophagus. Traditional diagnostic approaches, such as endoscopic examination, pathological analysis and computed tomography, require improvements in diagnostic precision and staging accuracy. Deep learning (DL), a key branch of artificial intelligence, shows great promise in improving the detection of early EC lesions, distinguishing benign from malignant lesions and aiding cancer staging and prognosis. However, challenges remain, including image quality variability, insufficient data annotation and limited generalization. The present review summarized recent advances in the application of DL to medical images obtained through various imaging techniques for the diagnosis of EC at different stages. It assesses the role of DL in tumor pathology, prognosis prediction and clinical decision support, highlighting its advantages in EC diagnosis and prognosis evaluation. Finally, it provided an objective analysis of the challenges currently facing the field and prospects for future applications.
Collapse
Affiliation(s)
- Aiting Lin
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, P.R. China
- Department of Thoracic Surgery, The Second Affiliated Hospital of Naval Medical University, Shanghai 200003, P.R. China
| | - Lirong Song
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, P.R. China
| | - Ying Wang
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, P.R. China
| | - Kai Yan
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai 200433, P.R. China
| | - Hua Tang
- Department of Thoracic Surgery, The Second Affiliated Hospital of Naval Medical University, Shanghai 200003, P.R. China
| |
Collapse
|
|
2
|
Chinzon M, Barbosa Marques S, Guimarães Hourneaux de Moura E. Extensive Esophageal Papillomatosis: A Rare Disease With Difficult Diagnosis. ACG Case Rep J 2025; 12:e01638. [PMID: 40018695 PMCID: PMC11864303 DOI: 10.14309/crj.0000000000001638] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/16/2024] [Accepted: 02/04/2025] [Indexed: 03/01/2025] Open
Abstract
Extensive esophageal papillomatosis is a rare condition with uncertain pathophysiology. We present a case involving a 78-year-old woman, with no notable habits or addictions, who presented with dysphagia and weight loss. She was diagnosed with extensive esophageal papillomatosis, causing esophageal substenosis. Diagnosis of dysplasia in such cases are challenging, and management of the risk of malignant transformation remains uncertain.
Collapse
Affiliation(s)
- Miriam Chinzon
- Gastrointestinal Endoscopy Unit, Division of Gastroenterology, Hospital das Clínicas of the Faculty of Medicine of the University of São Paulo – HC/FMUSP, Sao Paulo, Brazil
| | - Sergio Barbosa Marques
- Gastrointestinal Endoscopy Unit, Division of Gastroenterology, Hospital das Clínicas of the Faculty of Medicine of the University of São Paulo – HC/FMUSP, Sao Paulo, Brazil
| | - Eduardo Guimarães Hourneaux de Moura
- Gastrointestinal Endoscopy Unit, Division of Gastroenterology, Hospital das Clínicas of the Faculty of Medicine of the University of São Paulo – HC/FMUSP, Sao Paulo, Brazil
| |
Collapse
|
|
3
|
Li S, Xu M, Meng Y, Sun H, Zhang T, Yang H, Li Y, Ma X. The application of the combination between artificial intelligence and endoscopy in gastrointestinal tumors. MEDCOMM – ONCOLOGY 2024; 3. [DOI: 10.1002/mog2.91] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/29/2023] [Accepted: 09/03/2024] [Indexed: 01/04/2025]
Abstract
AbstractGastrointestinal (GI) tumors have always been a major type of malignant tumor and a leading cause of tumor‐related deaths worldwide. The main principles of modern medicine for GI tumors are early prevention, early diagnosis, and early treatment, with early diagnosis being the most effective measure. Endoscopy, due to its ability to visualize lesions, has been one of the primary modalities for screening, diagnosing, and treating GI tumors. However, a qualified endoscopist often requires long training and extensive experience, which to some extent limits the wider use of endoscopy. With advances in data science, artificial intelligence (AI) has brought a new development direction for the endoscopy of GI tumors. AI can quickly process large quantities of data and images and improve diagnostic accuracy with some training, greatly reducing the workload of endoscopists and assisting them in early diagnosis. Therefore, this review focuses on the combined application of endoscopy and AI in GI tumors in recent years, describing the latest research progress on the main types of tumors and their performance in clinical trials, the application of multimodal AI in endoscopy, the development of endoscopy, and the potential applications of AI within it, with the aim of providing a reference for subsequent research.
Collapse
Affiliation(s)
- Shen Li
- Department of Biotherapy Cancer Center, West China Hospital, West China Medical School Sichuan University Chengdu China
| | - Maosen Xu
- Laboratory of Aging Research and Cancer Drug Target, State Key Laboratory of Biotherapy, West China Hospital, National Clinical Research, Sichuan University Chengdu Sichuan China
| | - Yuanling Meng
- West China School of Stomatology Sichuan University Chengdu Sichuan China
| | - Haozhen Sun
- College of Life Sciences Sichuan University Chengdu Sichuan China
| | - Tao Zhang
- Department of Biotherapy Cancer Center, West China Hospital, West China Medical School Sichuan University Chengdu China
| | - Hanle Yang
- Department of Biotherapy Cancer Center, West China Hospital, West China Medical School Sichuan University Chengdu China
| | - Yueyi Li
- Department of Biotherapy Cancer Center, West China Hospital, West China Medical School Sichuan University Chengdu China
| | - Xuelei Ma
- Department of Biotherapy Cancer Center, West China Hospital, West China Medical School Sichuan University Chengdu China
| |
Collapse
|
|
4
|
Yu YB. Risk factors for lymph node metastasis in superficial esophageal squamous cell carcinoma. World J Gastroenterol 2024; 30:1810-1814. [PMID: 38659479 PMCID: PMC11036495 DOI: 10.3748/wjg.v30.i13.1810] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/06/2024] [Revised: 02/01/2024] [Accepted: 03/13/2024] [Indexed: 04/03/2024] Open
Abstract
In this editorial, we comment on the article by Wang et al published in the recent issue of the World Journal of Gastroenterology in 2023. We focused on identifying risk factors for lymph node metastasis (LNM) in superficial esophageal squamous cell carcinoma (SESCC) patients and how to construct a simple and reliable clinical prediction model to assess the risk of LNM in SESCC patients, thereby helping to guide the selection of an appropriate treatment plan. The current standard treatment for SESCC is radical esophagectomy with lymph node dissection. However, esophagectomy is associated with considerable morbidity and mortality. Endoscopic resection (ER) offers a safer and less invasive alternative to surgical resection and can enable the patient's quality of life to be maintained while providing a satisfactory outcome. However, since ER is a localized treatment that does not allow for lymph node dissection, the risk of LNM in SESCC limits the effectiveness of ER. Understanding LNM status can aid in determining whether patients with SESCC can be cured by ER without the need for additional esophagectomy. Previous studies have shown that tumor size, macroscopic type of tumor, degree of differentiation, depth of tumor invasion, and lymphovascular invasion are factors associated with LNM in patients with SESCC. In addition, tumor budding is commonly associated with LNM, recurrence, and distant metastasis, but this topic has been less covered in previous studies. By comprehensively evaluating the above risk factors for LNM, useful evidence can be obtained for doctors to select appropriate treatments for SESCC patients.
Collapse
Affiliation(s)
- Yan-Bo Yu
- Department of Gastroenterology, Laboratory of Translational Gastroenterology, Qilu Hospital, Shandong University, Jinan 250012, Shandong Province, China
| |
Collapse
|
|
5
|
Wang J, Long Q, Liang Y, Song J, Feng Y, Li P, Sun W, Zhao L. AI-assisted identification of intrapapillary capillary loops in magnification endoscopy for diagnosing early-stage esophageal squamous cell carcinoma: a preliminary study. Med Biol Eng Comput 2023:10.1007/s11517-023-02777-3. [PMID: 36841920 DOI: 10.1007/s11517-023-02777-3] [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: 07/21/2022] [Accepted: 12/22/2022] [Indexed: 02/27/2023]
Abstract
Esophageal squamous cell carcinoma (ESCC) is one of the most common histological types of esophageal cancers. It can seriously affect public health, particularly in Eastern Asia. Early diagnosis and effective therapy of ESCC can significantly help improve patient prognoses. The visualization of intrapapillary capillary loops (IPCLs) under magnification endoscopy (ME) can greatly support the identification of ESCC occurrences by endoscopists. This paper proposes an artificial-intelligence-assisted endoscopic diagnosis approach using deep learning for localizing and identifying IPCLs to diagnose early-stage ESCC. An improved Faster region-based convolutional network (R-CNN) with a polarized self-attention (PSA)-HRNetV2p backbone was employed to automatically detect IPCLs in ME images. In our study, 2887 ME with blue laser imaging (ME-BLI) images of 246 patients and 493 ME with narrow-band imaging (ME-NBI) images of 81 patients were collected from multiple hospitals and used to train and test our detection model. The ME-NBI images were used as the external testing set to verify the generalizability of the model. The experimental evaluation revealed that the proposed method achieved a recall of 79.25%, precision of 75.54%, F1-score of 0.764 and mean average precision (mAP) of 74.95%. Our method outperformed other existing approaches in our evaluation. It can effectively improve the accuracy of ESCC detection and provide a useful adjunct to the assessment of early-stage ESCC for endoscopists.
Collapse
Affiliation(s)
- Jinming Wang
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230026, China.,Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China
| | - Qigang Long
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230026, China.,Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China
| | - Yan Liang
- Department of Gastroenterology, Zhongda Hospital Affiliated to Southeast University, Nanjing, 210009, China
| | - Jie Song
- Department of Gastroenterology, Zhongda Hospital Affiliated to Southeast University, Nanjing, 210009, China
| | - Yadong Feng
- Department of Gastroenterology, Zhongda Hospital Affiliated to Southeast University, Nanjing, 210009, China
| | - Peng Li
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China
| | - Wei Sun
- School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230026, China.,Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China
| | - Lingxiao Zhao
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China.
| |
Collapse
|
|
6
|
Tokat M, van Tilburg L, Koch AD, Spaander MCW. Artificial Intelligence in Upper Gastrointestinal Endoscopy. Dig Dis 2021; 40:395-408. [PMID: 34348267 DOI: 10.1159/000518232] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/21/2021] [Accepted: 06/23/2021] [Indexed: 02/02/2023]
Abstract
BACKGROUND Over the past decade, several artificial intelligence (AI) systems are developed to assist in endoscopic assessment of (pre-)cancerous lesions of the gastrointestinal (GI) tract. In this review, we aimed to provide an overview of the possible indications of AI technology in upper GI endoscopy and hypothesize about potential challenges for its use in clinical practice. SUMMARY Application of AI in upper GI endoscopy has been investigated for several indications: (1) detection, characterization, and delineation of esophageal and gastric cancer (GC) and their premalignant conditions; (2) prediction of tumor invasion; and (3) detection of Helicobacter pylori. AI systems show promising results with an accuracy of up to 99% for the detection of superficial and advanced upper GI cancers. AI outperformed trainee and experienced endoscopists for the detection of esophageal lesions and atrophic gastritis. For GC, AI outperformed mid-level and trainee endoscopists but not expert endoscopists. KEY MESSAGES Application of artificial intelligence (AI) in upper gastrointestinal endoscopy may improve early diagnosis of esophageal and gastric cancer and may enable endoscopists to better identify patients eligible for endoscopic resection. The benefit of AI on the quality of upper endoscopy still needs to be demonstrated, while prospective trials are needed to confirm accuracy and feasibility during real-time daily endoscopy.
Collapse
Affiliation(s)
- Meltem Tokat
- Department of Gastroenterology and Hepatology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - Laurelle van Tilburg
- Department of Gastroenterology and Hepatology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - Arjun D Koch
- Department of Gastroenterology and Hepatology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - Manon C W Spaander
- Department of Gastroenterology and Hepatology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, The Netherlands
| |
Collapse
|
|
7
|
Murakami D, Harada H, Yamato M, Amano Y. Cytomegalovirus-associated esophagitis on early esophageal cancer in immunocompetent host: a case report. Gut Pathog 2021; 13:24. [PMID: 33863376 PMCID: PMC8051061 DOI: 10.1186/s13099-021-00418-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/11/2020] [Accepted: 04/01/2021] [Indexed: 11/28/2022] Open
Abstract
Background Cytomegalovirus (CMV)-associated gastrointestinal diseases usually occur in immunocompromised patients; however, few cases has also been described in healthy hosts despite still unclear pathological mechanisms. CMV esophagitis causes various lesions, such as erythematous mucosa, erosions, and ulcers, although such inflammatory changes can appear in superficial esophageal cancers or in surrounding areas. CMV-associated esophagitis has been also reported in cancer patients, but typically in those with advanced and/or terminal stage cancers secondary to chemoradiotherapy-induced immunosuppression or the physiologic demands of the malignancy itself. To our best knowledge, we firstly report on an immunocompetent patient subject to endoscopic submucosal dissection (ESD) for early esophageal cancer complicated with CMV infection. Case presentation A 77-year-old man underwent esophagogastroduodenoscopy (EGD) at a local clinic. EGD revealed a lugol-unstained reddish lesion with whitish exudates in the middle-distal esophagus. Histological evaluation of lesion biopsy revealed atypical squamous epithelium with CMV-positive granulation tissue and aggregates of macrophages, prompting referral for further examination and treatment. Magnifying endoscopy with narrow-band imaging showed an erosive lesion with white moss in a well-demarcated brownish area with irregular mesh-like microvessels. ESD was performed for diagnosis and treatment. Histopathological examination of the resected specimen revealed superficial, moderately differentiated squamous cell carcinoma (SCC) with multiple lymphatic infiltration, and few CMV-positive cells were found in the erosive part of the SCC. Interestingly, he had no underlying conditions to predispose to CMV infection and no risk factors for esophageal cancer, other than gender and age. He received neither steroids for stricture prevention nor antiviral agents post-EGD and 4-month follow-up was negative for esophagitis. Conclusions This is the first report of a case of CMV esophagitis superimposed on early esophageal cancer in an immunocompetent host and might provide valuable information for possible adverse effects of steroid administration during ESD procedures, despite their common use for prevention of post-ESD stricture.
Collapse
Affiliation(s)
- Daisuke Murakami
- Department of Gastroenterology, New Tokyo Hospital, 1271 Wanagaya, Matsudo, Chiba, 270-2232, Japan. .,Institute of Advanced Biomedical Engineering and Science, Tokyo Women's Medical University, 8-1, Kawada-cho, Shinjuku-ku, Tokyo, 162-8666, Japan. .,Department of Gastroenterology, Tokyo Women's Medical University Yachiyo Medical Center, 477-96 Owadashinden, Yachiyo, Chiba, 276-8524, Japan.
| | - Hideaki Harada
- Department of Gastroenterology, New Tokyo Hospital, 1271 Wanagaya, Matsudo, Chiba, 270-2232, Japan
| | - Masayuki Yamato
- Institute of Advanced Biomedical Engineering and Science, Tokyo Women's Medical University, 8-1, Kawada-cho, Shinjuku-ku, Tokyo, 162-8666, Japan
| | - Yuji Amano
- Department of Endoscopy, New Tokyo Hospital, 1271 Wanagaya, Matsudo, Chiba, 270-2232, Japan
| |
Collapse
|