Development and validation of a deep learning-based approach to predict the Mayo endoscopic score of ulcerative colitis
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....
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-05-01
|
| Series: | Therapeutic Advances in Gastroenterology |
| Online Access: | https://doi.org/10.1177/17562848231170945 |
| _version_ | 1827942858162700288 |
|---|---|
| author | Jing Qi Guangcong Ruan Yi Ping Zhifeng Xiao Kaijun Liu Yi Cheng Rongbei Liu Bingqiang Zhang Min Zhi Junrong Chen Fang Xiao Tingting Zhao Jiaxing Li Zhou Zhang Yuxin Zou Qian Cao Yongjian Nian Yanling Wei |
| author_facet | Jing Qi Guangcong Ruan Yi Ping Zhifeng Xiao Kaijun Liu Yi Cheng Rongbei Liu Bingqiang Zhang Min Zhi Junrong Chen Fang Xiao Tingting Zhao Jiaxing Li Zhou Zhang Yuxin Zou Qian Cao Yongjian Nian Yanling Wei |
| author_sort | Jing Qi |
| collection | DOAJ |
| description | 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) |
| first_indexed | 2024-03-13T10:05:49Z |
| format | Article |
| id | doaj.art-d341906ab1d74b22b51f319239af653c |
| institution | Directory Open Access Journal |
| issn | 1756-2848 |
| language | English |
| last_indexed | 2024-03-13T10:05:49Z |
| publishDate | 2023-05-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Therapeutic Advances in Gastroenterology |
| spelling | doaj.art-d341906ab1d74b22b51f319239af653c2023-05-22T13:03:39ZengSAGE PublishingTherapeutic Advances in Gastroenterology1756-28482023-05-011610.1177/17562848231170945Development and validation of a deep learning-based approach to predict the Mayo endoscopic score of ulcerative colitisJing QiGuangcong RuanYi PingZhifeng XiaoKaijun LiuYi ChengRongbei LiuBingqiang ZhangMin ZhiJunrong ChenFang XiaoTingting ZhaoJiaxing LiZhou ZhangYuxin ZouQian CaoYongjian NianYanling WeiBackground: 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)https://doi.org/10.1177/17562848231170945 |
| spellingShingle | Jing Qi Guangcong Ruan Yi Ping Zhifeng Xiao Kaijun Liu Yi Cheng Rongbei Liu Bingqiang Zhang Min Zhi Junrong Chen Fang Xiao Tingting Zhao Jiaxing Li Zhou Zhang Yuxin Zou Qian Cao Yongjian Nian Yanling Wei Development and validation of a deep learning-based approach to predict the Mayo endoscopic score of ulcerative colitis Therapeutic Advances in Gastroenterology |
| title | Development and validation of a deep learning-based approach to predict the Mayo endoscopic score of ulcerative colitis |
| title_full | Development and validation of a deep learning-based approach to predict the Mayo endoscopic score of ulcerative colitis |
| title_fullStr | Development and validation of a deep learning-based approach to predict the Mayo endoscopic score of ulcerative colitis |
| title_full_unstemmed | Development and validation of a deep learning-based approach to predict the Mayo endoscopic score of ulcerative colitis |
| title_short | Development and validation of a deep learning-based approach to predict the Mayo endoscopic score of ulcerative colitis |
| title_sort | development and validation of a deep learning based approach to predict the mayo endoscopic score of ulcerative colitis |
| url | https://doi.org/10.1177/17562848231170945 |
| work_keys_str_mv | AT jingqi developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT guangcongruan developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT yiping developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT zhifengxiao developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT kaijunliu developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT yicheng developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT rongbeiliu developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT bingqiangzhang developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT minzhi developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT junrongchen developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT fangxiao developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT tingtingzhao developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT jiaxingli developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT zhouzhang developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT yuxinzou developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT qiancao developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT yongjiannian developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis AT yanlingwei developmentandvalidationofadeeplearningbasedapproachtopredictthemayoendoscopicscoreofulcerativecolitis |