Evaluation of Computer‐aided Detection for Identifying Missed Gastric Cancer After Endoscopic Submucosal Dissection
Tatsunori Minamide, Tomonori Sato, Seiichiro Sakaguchi, Noboru Kawata, Yuki Maeda, Masao Yoshida, Yoichi Yamamoto, Taishi Okumura, Tetsuya Suwa, Hiroshi Ashizawa, Kohei Shigeta, Haruka Nakamura, Akifumi Notsu, Toshio Uraoka, Hiroyuki OnoABSTRACT
Objectives
Computer‐aided detection (CADe) using deep learning is promising for reducing missed gastric cancers (MGCs) and supporting physicians in double‐checking endoscopic images. We aimed to evaluate the CADe efficacy for MGCs after endoscopic submucosal dissection (ESD).
Methods
We collected 2324 endoscopic images, including 60 of MGCs detected during surveillance esophagogastroduodenoscopy within 18 months after initial ESD. The performance of the CADe system, developed for early GC detection using deep learning, was compared with that of 10 endoscopists in a detection study using collected images. Per‐lesion sensitivity, per‐image detection performance, and diagnostic time were compared.
Results
The per‐lesion sensitivity for MGCs was 15.0% (9/60) and 13.8% (83/600) for CADe and endoscopist detection, respectively ( p = 0.538). The respective per‐image computer‐aided and endoscopist performance sensitivity was 11.3% and 10.6% ( p = 0.548), specificity 88.5% and 94.8% ( p < 0.001), positive predictive value 4.4% and 8.3%, and negative predictive value 95.7% and 96.0%. The per‐image CADe time was significantly shorter (0.03 s vs. 2.86 s, p < 0.001). CADe showed higher sensitivity in certain subgroups, although these findings should be interpreted cautiously given the small sample size.
Conclusions
No significant difference in sensitivity was observed between CADe and endoscopist detection for MGCs after ESD, and the absolute sensitivity remained low. Further improvements are needed before clinical implementation of CADe as a double‐checking tool.
Trial Registration
The authors have confirmed clinical trial registration is not needed for this submission.