A deep learning-based computer-aided diagnosis system for detecting atypical endometrial hyperplasia and endometrial cancer through hysteroscopy
Summary: Timely diagnosis of endometrial cancer (EC) and atypical endometrial hyperplasia (AEH) is crucial, yet traditional hysteroscopy faces accuracy challenges. This study introduces ECCADx, a deep learning-based computer-aided diagnosis system utilizing contrastive learning for hysteroscopic ide...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-08-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004225013069 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850102904660164608 |
|---|---|
| author | Wenwen Wang Yuyang Cai Zhe Guo Aihua Zhao Wenqing Ma Wuliang Wang Shixuan Wang Xin Zhu Xin Du Wenfeng Shen |
| author_facet | Wenwen Wang Yuyang Cai Zhe Guo Aihua Zhao Wenqing Ma Wuliang Wang Shixuan Wang Xin Zhu Xin Du Wenfeng Shen |
| author_sort | Wenwen Wang |
| collection | DOAJ |
| description | Summary: Timely diagnosis of endometrial cancer (EC) and atypical endometrial hyperplasia (AEH) is crucial, yet traditional hysteroscopy faces accuracy challenges. This study introduces ECCADx, a deep learning-based computer-aided diagnosis system utilizing contrastive learning for hysteroscopic identification of AEH and EC. This is the system to integrate contrastive learning for this specific differentiation. ECCADx leveraged contrastive learning during pre-training on diverse external medical images, extracting robust features. Trained on 49,646 images from 1,204 patients, it underwent rigorous multicenter validation on two independent test datasets (6,228 images from 190 patients). ECCADx consistently achieved high diagnostic accuracy, often surpassing experienced endoscopists. Notably, it attained 95.2% sensitivity and 91.3% specificity on the internal dataset, and 92.1% sensitivity with 100% specificity on the external dataset. ECCADx proves a reliable tool, comparable or superior to human experts, promising to reduce misdiagnosis and improve patient outcomes. |
| format | Article |
| id | doaj-art-18c824aa712d43768a13641e910eb2ab |
| institution | DOAJ |
| issn | 2589-0042 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj-art-18c824aa712d43768a13641e910eb2ab2025-08-20T02:39:40ZengElsevieriScience2589-00422025-08-0128811304510.1016/j.isci.2025.113045A deep learning-based computer-aided diagnosis system for detecting atypical endometrial hyperplasia and endometrial cancer through hysteroscopyWenwen Wang0Yuyang Cai1Zhe Guo2Aihua Zhao3Wenqing Ma4Wuliang Wang5Shixuan Wang6Xin Zhu7Xin Du8Wenfeng Shen9Department of Obstetrics and Gynecology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Computer and Information Engineering, Shanghai Polytechnic University, Shanghai, ChinaGraduate School of Computer Science and Engineering, The University of Aizu, Aizu-Wakamatsu, Japan; Department of Laboratory Medicine, The Second Xiangya Hospital, Central South University, Changsha, ChinaGraduate School of Computer Science and Engineering, The University of Aizu, Aizu-Wakamatsu, Japan; College of Virtual Reality Modern Industry, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, ChinaDepartment of Obstetrics and Gynecology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Obstetrics and Gynecology, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, ChinaDepartment of Obstetrics and Gynecology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of AI Technology Development, M&D Data Science Center, Institute of Integrated Research, Institute of Science Tokyo, Tokyo, Japan; Corresponding authorDepartment of Gynecology, Maternal and Child Health Hospital of Hubei Province, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China; Corresponding authorSchool of Computer and Information Engineering, Shanghai Polytechnic University, Shanghai, China; Corresponding authorSummary: Timely diagnosis of endometrial cancer (EC) and atypical endometrial hyperplasia (AEH) is crucial, yet traditional hysteroscopy faces accuracy challenges. This study introduces ECCADx, a deep learning-based computer-aided diagnosis system utilizing contrastive learning for hysteroscopic identification of AEH and EC. This is the system to integrate contrastive learning for this specific differentiation. ECCADx leveraged contrastive learning during pre-training on diverse external medical images, extracting robust features. Trained on 49,646 images from 1,204 patients, it underwent rigorous multicenter validation on two independent test datasets (6,228 images from 190 patients). ECCADx consistently achieved high diagnostic accuracy, often surpassing experienced endoscopists. Notably, it attained 95.2% sensitivity and 91.3% specificity on the internal dataset, and 92.1% sensitivity with 100% specificity on the external dataset. ECCADx proves a reliable tool, comparable or superior to human experts, promising to reduce misdiagnosis and improve patient outcomes.http://www.sciencedirect.com/science/article/pii/S2589004225013069Computer-aided diagnosis methodCancerMachine learning |
| spellingShingle | Wenwen Wang Yuyang Cai Zhe Guo Aihua Zhao Wenqing Ma Wuliang Wang Shixuan Wang Xin Zhu Xin Du Wenfeng Shen A deep learning-based computer-aided diagnosis system for detecting atypical endometrial hyperplasia and endometrial cancer through hysteroscopy iScience Computer-aided diagnosis method Cancer Machine learning |
| title | A deep learning-based computer-aided diagnosis system for detecting atypical endometrial hyperplasia and endometrial cancer through hysteroscopy |
| title_full | A deep learning-based computer-aided diagnosis system for detecting atypical endometrial hyperplasia and endometrial cancer through hysteroscopy |
| title_fullStr | A deep learning-based computer-aided diagnosis system for detecting atypical endometrial hyperplasia and endometrial cancer through hysteroscopy |
| title_full_unstemmed | A deep learning-based computer-aided diagnosis system for detecting atypical endometrial hyperplasia and endometrial cancer through hysteroscopy |
| title_short | A deep learning-based computer-aided diagnosis system for detecting atypical endometrial hyperplasia and endometrial cancer through hysteroscopy |
| title_sort | deep learning based computer aided diagnosis system for detecting atypical endometrial hyperplasia and endometrial cancer through hysteroscopy |
| topic | Computer-aided diagnosis method Cancer Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2589004225013069 |
| work_keys_str_mv | AT wenwenwang adeeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT yuyangcai adeeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT zheguo adeeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT aihuazhao adeeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT wenqingma adeeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT wuliangwang adeeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT shixuanwang adeeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT xinzhu adeeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT xindu adeeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT wenfengshen adeeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT wenwenwang deeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT yuyangcai deeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT zheguo deeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT aihuazhao deeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT wenqingma deeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT wuliangwang deeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT shixuanwang deeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT xinzhu deeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT xindu deeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy AT wenfengshen deeplearningbasedcomputeraideddiagnosissystemfordetectingatypicalendometrialhyperplasiaandendometrialcancerthroughhysteroscopy |