A computer-aided diagnosis system using white-light endoscopy for the prediction of conventional adenoma with high grade dysplasia |
| |
| Institution: | 1. Center for Digestive Disease, the Seventh Affiliated Hospital of Sun Yat-sen University, No. 628, Zhenyuan Rd, Guangming (New) District, Shenzhen, Guangdong 518107, China;2. The Third Clinical Medical College, Fujian Medical University, Fuzhou, Fujian 350004, China;3. Department of Gastroenterology, zhongshan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian 361004, China;4. Zhejiang Provincial People''s Hospital, People''s Hospital of Hangzhou Medical College, No. 158 of Shangtang Road, XiaCheng District, Hangzhou, Zhejiang 310014, China;5. Tongxiang First People''s Hospital, Tongxiang City, Zhejiang 353000, China;6. Pucheng County Hospital of Traditional Chinese Medicine, Pucheng, Fujian 353400, China;7. Jiying (XiaMen) Technology Co., LTD, Xiamen, Fujian 361004, China;8. Xiamen Cingene Science and technology co., LTD, Xiamen, Fujian 361004, China;9. State Key Laboratory of Marine Environmental Science, College of Ocean and Earth Sciences, Xiamen University, Xiamen 361102, China;10. Friedman Brain Institute, Icahn School of Medicine at Mount Sinai, New York, NY 10029, United States;11. University of Pennsylvania Perelman School of Medicine, Philadelphia, United States;12. The School of Pharmacy in Fujian Medical University, No.1 Qiuyang Road, Fujian 350122, China;13. College of Pharmacy, Fujian University of Traditional Chinese Medicine, Shangjie University Town, Fuzhou, Fujian 350122, China;14. School of Life Sciences, Xiamen University, Xiamen, Fujian 36110, China;15. Department of Clinical Pharmacy, First Hospital of Nanping, Fujian 314500, China;p. Department of Financial Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, United States |
| |
| Abstract: | ObjectivesWe developed a computer-aided diagnosis system called ECRC CAD using standard white-light endoscopy (WLE) for predicting conventional adenomas with high-grade dysplasia (HGD) to optimise the patients' management decisions during colonoscopy.MethodsPretraining model was used to fine-tune the model parameters by transfer learning. 2,397 images of HGD and 2,487 low-grade dysplasia (LGD) images were randomly assigned (8:1:1) to the training, optimising, and internal validation dataset. The prospective validation dataset is the frames accessed from colonoscope videoes. One independent rural hospital provided an external validation dataset. Histopathological diagnosis was used as the standard criterion. The capability of the ECRCCAD to distinguish HGD was assessed and compared with two expert endoscopists.ResultsThe accuracy, sensitivity and specificity for diagnosis of HGD in the internal validation set were 90.5%, 93.2%, 87.9%, respectively. While 88.2%, 85.4%, 89.8%, respectively, for the external validation set. For the prospective validation set, ECRCCAD achieved an AUC of 93.5% in diagnosing HGD. The performance of ECRCCAD in diagnosing HGD was better than that of the expert endoscopist in the external validation set (88.2% vs. 71.5%, P < 0.0001).ConclusionECRCCAD had good diagnostic capability for HGD and enabled a more convenient and accurate diagnosis using WLE. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
