Ping An1,2,3, Dongmei Yang1,2,3, Jing Wang1,2,3, Lianlian Wu1,2,3, Jie Zhou1,2,3, Zhi Zeng4, Xu Huang1,2,3, Yong Xiao1,2,3, Shan Hu5, Yiyun Chen5, Fang Yao6, Mingwen Guo7, Qi Wu8, Yanning Yang9, Honggang Yu10,11,12. 1. Department of Gastroenterology, Renmin Hospital of Wuhan University, 99 Zhangzhidong Road, Wuhan, 430060, Hubei Province, China. 2. Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China. 3. Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China. 4. Department of Pathology, Renmin Hospital of Wuhan University, Wuhan, China. 5. School of Resources and Environmental Sciences of Wuhan University, Wuhan, China. 6. Department of Gastroenterology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China. 7. Department of Gastroenterology, The first hospital of Yichang, Yichang, China. 8. Department of Endoscopy, Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Peking University Cancer Hospital & Institute, Beijing, China. 9. Department of Ophthalmology, Renmin Hospital of Wuhan University, 99 Zhangzhidong Road, Wuhan, 430060, Hubei Province, China. ophyyn@163.com. 10. Department of Gastroenterology, Renmin Hospital of Wuhan University, 99 Zhangzhidong Road, Wuhan, 430060, Hubei Province, China. yuhonggang@whu.edu.cn. 11. Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China. yuhonggang@whu.edu.cn. 12. Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China. yuhonggang@whu.edu.cn.
Abstract
BACKGROUND: Accurate delineation of cancer margins is critical for endoscopic curative resection. This study aimed to train and validate real-time fully convolutional networks for delineating the resection margin of early gastric cancer (EGC) under indigo carmine chromoendoscopy (CE) or white light endoscopy (WLE), and evaluated its performance and that of magnifying endoscopy with narrow-band imaging (ME-NBI). METHODS: We collected CE and WLE images of EGC lesions to train fully convolutional networks ENDOANGEL. ENDOANGEL was tested both on stationary images and endoscopic submucosal dissection (ESD) videos. The accuracy and reliability of ENDOANGEL and NBI-dependent delineation were further evaluated by a novel endoscopy-pathology point-to-point marking. RESULTS: ENDOANGEL had an accuracy of 85.7% in the CE images and 88.9% in the WLE images under an overlap ratio threshold of 0.60 in comparison with the manual markers labeled by the experts. In the ESD videos, the resection margins predicted by ENDOANGEL covered all areas of high-grade intraepithelial neoplasia and cancers. The minimum distance between the margins predicted by ENDOANGEL and the histological cancer boundary was 3.44 ± 1.45 mm which outperformed the resection margin based on ME-NBI. CONCLUSIONS: ENDOANGEL has the potential to assist endoscopists in delineating the resection extent of EGC under CE or WLE during ESD.
BACKGROUND: Accurate delineation of cancer margins is critical for endoscopic curative resection. This study aimed to train and validate real-time fully convolutional networks for delineating the resection margin of early gastric cancer (EGC) under indigo carmine chromoendoscopy (CE) or white light endoscopy (WLE), and evaluated its performance and that of magnifying endoscopy with narrow-band imaging (ME-NBI). METHODS: We collected CE and WLE images of EGC lesions to train fully convolutional networks ENDOANGEL. ENDOANGEL was tested both on stationary images and endoscopic submucosal dissection (ESD) videos. The accuracy and reliability of ENDOANGEL and NBI-dependent delineation were further evaluated by a novel endoscopy-pathology point-to-point marking. RESULTS: ENDOANGEL had an accuracy of 85.7% in the CE images and 88.9% in the WLE images under an overlap ratio threshold of 0.60 in comparison with the manual markers labeled by the experts. In the ESD videos, the resection margins predicted by ENDOANGEL covered all areas of high-grade intraepithelial neoplasia and cancers. The minimum distance between the margins predicted by ENDOANGEL and the histological cancer boundary was 3.44 ± 1.45 mm which outperformed the resection margin based on ME-NBI. CONCLUSIONS: ENDOANGEL has the potential to assist endoscopists in delineating the resection extent of EGC under CE or WLE during ESD.
Entities:
Keywords:
Chromoendoscopy; Early gastric cancer; Fully convolutional networks; Horizontal extent; White light endoscopy