A Deep Learning Method for Delineating Early Gastric Cancer Resection Margins Under Chromoendoscopy or White Light Endoscopy

Abstract

Background: Accurate delineation of cancer margins is critical for achieving endoscopic curative resection. This study aimed to train and validate real-time fully convolutional networks (FCNs) 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/WLE images of EGC lesions to train FCNs named ENDOANGEL. ENDOANGEL was tested both on still images and endoscopic submucosal dissection (ESD) videos and evaluated the performance of ME-NBI based on post-ESD pathology determined using endoscopy–pathology point-to-point marking. Findings: 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 makers made by the expert. In the ESD videos, the resection margins predicted by ENDOANGEL covered all areas of high-grade intraepithelial neoplasia and cancer. The minimum distance between the margins predicted by ENDOANGEL and the cancerous boundary confirmed by pathology was 3·44±1·45 mm, outperforming the resection margin based on ME-NBI. Interpretation: ENDOANGEL has the potential to assist endoscopists in delineating the resection extent of EGCs under CE or WLE during ESD. Funding Statement: Project of Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision (grant no. 2018BCC337); Hubei Province Major Science and Technology Innovation Project (grant no. 2018-916-000-008); the National Natural Science Foundation of China [grant no. 81672387 (to Yu Honggang)]; the National Natural Science Foundation of China [grant no. 81302131(to Ping An)]. Declaration of Interests: The authors stated: None. Ethics Approval Statement: The study protocol was approved by the ethics committee of Renmin Hospital of Wuhan University.