Development and validation of a deep learning-based approach to predict the Mayo endoscopic score of ulcerative colitis

作者全名："Qi, Jing; Ruan, Guangcong; Ping, Yi; Xiao, Zhifeng; Liu, Kaijun; Cheng, Yi; Liu, Rongbei; Zhang, Bingqiang; Zhi, Min; Chen, Junrong; Xiao, Fang; Zhao, Tingting; Li, Jiaxing; Zhang, Zhou; Zou, Yuxin; Cao, Qian; Nian, Yongjian; Wei, Yanling"

作者地址："[Wei, Yanling] Third Mil Med Univ, Army Med Univ, Daping Hosp, Dept Gastroenterol,Chongqing Key Lab Digest Malign, 10 Changjiang Branch Rd, Chongqing 400042, Peoples R China; [Nian, Yongjian] Third Mil Med Univ, Army Med Univ, Sch Biomed Engn & Imaging Med, Dept Digital Med, Chongqing 400038, Peoples R China; [Cao, Qian] Zhejiang Univ, Sir Run Run Shaw Hosp, Sch Med, Dept Gastroenterol, Hangzhou 310016, Peoples R China; [Qi, Jing; Zou, Yuxin] Army Med Univ, Sch Biomed Engn & Imaging Med, Dept Digital Med, Chongqing, Peoples R China; [Ruan, Guangcong; Ping, Yi; Xiao, Zhifeng; Liu, Kaijun; Cheng, Yi] Third Mil Med Univ, Army Med Univ, Daping Hosp, Dept Gastroenterol,Chongqing Key Lab Digest Malign, Chongqing, Peoples R China; [Liu, Rongbei; Zhang, Zhou] Zhejiang Univ, Sir Run Run Shaw Hosp, Sch Med, Dept Gastroenterol, Hangzhou, Peoples R China; [Zhang, Bingqiang] Chongqing Med Univ, Affiliated Hosp 1, Dept Gastroenterol, Chongqing, Peoples R China; [Zhi, Min; Chen, Junrong] Sun Yat Sen Univ, Affiliated Hosp 6, Dept Gastroenterol, Guangdong Prov Key Lab Colorectal & Pelv Floor Dis, Guangzhou, Peoples R China; [Xiao, Fang] Huazhong Univ Sci & Technol, Tongji Hosp, Tongji Med Coll, Dept Gastroenterol, Wuhan, Peoples R China; [Zhao, Tingting; Li, Jiaxing] Third Mil Med Univ 3, Army Med Univ, Sch Basic Med, Chongqing, Peoples R China"

通信作者："Wei, YL (通讯作者)，Third Mil Med Univ, Army Med Univ, Daping Hosp, Dept Gastroenterol,Chongqing Key Lab Digest Malign, 10 Changjiang Branch Rd, Chongqing 400042, Peoples R China.; Nian, YJ (通讯作者)，Third Mil Med Univ, Army Med Univ, Sch Biomed Engn & Imaging Med, Dept Digital Med, Chongqing 400038, Peoples R China.; Cao, Q (通讯作者)，Zhejiang Univ, Sir Run Run Shaw Hosp, Sch Med, Dept Gastroenterol, Hangzhou 310016, Peoples R China."

来源：THERAPEUTIC ADVANCES IN GASTROENTEROLOGY

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:000991741300001

JCR分区：Q1

影响因子：3.9

年份：2023

卷号：16

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：ulcerative colitis; Mayo endoscopy score; deep learning; vision transformer

摘要："Plain language summaryWhy was this study done?The development of an auxiliary diagnostic tool can reduce the workload of endoscopists and achieve rapid assessment of ulcerative colitis (UC) severity.What did the researchers do?We developed and validated a deep learning-based approach to automatically predict the Mayo endoscopic score using UC endoscopic images.What did the researchers find?The model that was developed in this study achieved high accuracy, fidelity, and stability, and demonstrated potential application in clinical practice.What do the findings mean?Deep learning could effectively assist endoscopists in evaluating the severity of UC in patients using endoscopic images. Background:The ulcerative colitis (UC) Mayo endoscopy score is a useful tool for evaluating the severity of UC in patients in clinical practice. Objectives:We aimed to develop and validate a deep learning-based approach to automatically predict the Mayo endoscopic score using UC endoscopic images. Design:A multicenter, diagnostic retrospective study. Methods:We collected 15120 colonoscopy images of 768 UC patients from two hospitals in China and developed a deep model based on a vision transformer named the UC-former. The performance of the UC-former was compared with that of six endoscopists on the internal test set. Furthermore, multicenter validation from three hospitals was also carried out to evaluate UC-former's generalization performance. Results:On the internal test set, the areas under the curve of Mayo 0, Mayo 1, Mayo 2, and Mayo 3 achieved by the UC-former were 0.998, 0.984, 0.973, and 0.990, respectively. The accuracy (ACC) achieved by the UC-former was 90.8%, which is higher than that achieved by the best senior endoscopist. For three multicenter external validations, the ACC was 82.4%, 85.0%, and 83.6%, respectively. Conclusions:The developed UC-former could achieve high ACC, fidelity, and stability to evaluate the severity of UC, which may provide potential application in clinical practice. Registration:This clinical trial was registered at the ClinicalTrials.gov (trial registration number: NCT05336773)"

基金机构：　

基金资助正文：