한빛사 논문
Jeonghyuk Park1,*; Bo Gun Jang2,*; Yeong Won Kim1; Hyunho Park1; Baek-hui Kim3; Myung Ju Kim4; Hyungsuk Ko5; Jae Moon Gwak5; Eun Ji Lee5; Yul Ri Chung5; Kyungdoc Kim1; Jae Kyung Myung6; Jeong Hwan Park7; Dong Youl Choi5; Chang Won Jung5; Bong-Hee Park5; Kyu-Hwan Jung1,†; Dong-Il Kim5,†
1VUNO Inc., Seoul, South Korea, 2Department of Pathology, Jeju National University School of Medicine and Jeju National University Hospital, Jeju, South Korea, 3Department of Pathology, Korea University Guro Hospital, Seoul, South Korea, 4Department of Anatomy, Dankook University College of Medicine, Chonan, Chungnam, South Korea, 5Department of Pathology, Green Cross Laboratories, Yongin, Gyeonggi, South Korea, 6Department of Pathology, College of Medicine, Hanyang University, Seoul, South Korea, 7Department of Pathology, SMG-SNU Boramae Medical Center, Seoul, South Korea
*,† these authors equally contributed to this paper
Abstract
Purpose: Gastric cancer remains the leading cause of cancer death in Northeast Asia. Population-based endoscopic screenings in the region have yielded successful results in early detection of gastric tumors. Subsequently, endoscopic screening rates are continuously increasing, and there is a need for an automatic computerized diagnostic system to reduce the diagnostic burden. In this study, we developed an algorithm to classify gastric epithelial tumors automatically and assessed its performance in a large series of gastric biopsies and its benefits as an assistance tool. Experimental Design: Using 2,434 whole slide images (WSIs), we developed an algorithm based on convolutional neural networks (CNN) to classify a gastric biopsy image into one of three categories: negative for dysplasia (NFD), tubular adenoma (TA), or carcinoma (CA). The performance of the algorithm was evaluated with 7,440 biopsy specimens collected prospectively. The impact of algorithm-assisted diagnosis was assessed by six pathologists using 150 gastric biopsy cases. Results: Diagnostic performance evaluated by the area under the receiver operating characteristic curve (AUROC) in the prospective study was 0.9790 for two-tier classification; negative (NFD) vs. positive (all cases except NFD). When limited to epithelial tumors, the sensitivity and specificity were 1.000 and 0.9749. Algorithm-assistance digital image viewer resulted in 47% reduction in review time per image compared to digital image viewer only and 58% decrease to microscopy. Conclusions: Our algorithm has demonstrated high accuracy in classifying epithelial tumors and its benefits as an assistance tool which can serve a potential screening aid system in diagnosing gastric biopsy specimens.
논문정보
관련 링크
연구자 키워드
관련분야 연구자보기
관련분야 논문보기
해당논문 저자보기