| Title | A deep learning method for delineating early gastric cancer resection margin under chromoendoscopy and white light endoscopy |
| Authors | An, Ping Yang, Dongmei Wang, Jing Wu, Lianlian Zhou, Jie Zeng, Zhi Huang, Xu Xiao, Yong Hu, Shan Chen, Yiyun Yao, Fang Guo, Mingwen Wu, Qi Yang, Yanning Yu, Honggang |
| Affiliation | Wuhan Univ, Dept Gastroenterol, Renmin Hosp, 99 Zhangzhidong Rd, Wuhan 430060, Hubei, Peoples R China Wuhan Univ, Key Lab Hubei Prov Digest Syst Dis, Renmin Hosp, Wuhan, Peoples R China Wuhan Univ, Hubei Prov Clin Res Ctr Digest Dis Minimally Inva, Renmin Hosp, Wuhan, Peoples R China Wuhan Univ, Dept Pathol, Renmin Hosp, Wuhan, Peoples R China Wuhan Univ, Sch Resources & Environm Sci, Wuhan, Peoples R China Chinese Acad Med Sci & Peking Union Med Coll, Peking Union Med Coll Hosp, Dept Gastroenterol, Beijing, Peoples R China First Hosp Yichang, Dept Gastroenterol, Yichang, Peoples R China Peking Univ, Dept Endoscopy, Key Lab Carcinogenesis & Translat Res, Minist Educ,Canc Hosp & Inst, Beijing, Peoples R China Wuhan Univ, Dept Ophthalmol, Renmin Hosp, 99 Zhangzhidong Rd, Wuhan 430060, Hubei, Peoples R China |
| Keywords | INDIGO CARMINE DYE MAGNIFYING ENDOSCOPY SUBMUCOSAL DISSECTION HORIZONTAL EXTENT ACETIC-ACID DIAGNOSIS CLASSIFICATION |
| Issue Date | Apr-2020 |
| Publisher | GASTRIC CANCER |
| 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. |
| URI | http://hdl.handle.net/20.500.11897/606765 |
| ISSN | 1436-3291 |
| DOI | 10.1007/s10120-020-01071-7 |
| Indexed | SCI(E) |
| Appears in Collections: | 北京肿瘤医院 |
