Zhao Youshen, Dohi Osamu, Ishida Tsugitaka, Yoshida Naohisa, Ochiai Tomoko, Mukai Hiroki, Seya Mayuko, Yamauchi Katsuma, Miyazaki Hajime, Fukui Hayato, Yasuda Takeshi, Iwai Naoto, Inoue Ken, Itoh Yoshito, Liu Xinkai, Zhang Ruiyao, Zhu Xin
Graduate School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Fukushima, Japan.
Molecular Gastroenterology and Hepatology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan.
Dig Dis. 2024;42(6):503-511. doi: 10.1159/000540728. Epub 2024 Aug 5.
Esophagogastroduodenoscopy is the most important tool to detect gastric cancer (GC). In this study, we developed a computer-aided detection (CADe) system to detect GC with white light imaging (WLI) and linked color imaging (LCI) modes and aimed to compare the performance of CADe with that of endoscopists.
The system was developed based on the deep learning framework from 9,021 images in 385 patients between 2017 and 2020. A total of 116 LCI and WLI videos from 110 patients between 2017 and 2023 were used to evaluate per-case sensitivity and per-frame specificity.
The per-case sensitivity and per-frame specificity of CADe with a confidence level of 0.5 in detecting GC were 78.6% and 93.4% for WLI and 94.0% and 93.3% for LCI, respectively (p < 0.001). The per-case sensitivities of nonexpert endoscopists for WLI and LCI were 45.8% and 80.4%, whereas those of expert endoscopists were 66.7% and 90.6%, respectively. Regarding detectability between CADe and endoscopists, the per-case sensitivities for WLI and LCI were 78.6% and 94.0% in CADe, respectively, which were significantly higher than those for LCI in experts (90.6%, p = 0.004) and those for WLI and LCI in nonexperts (45.8% and 80.4%, respectively, p < 0.001); however, no significant difference for WLI was observed between CADe and experts (p = 0.134).
Our CADe system showed significantly better sensitivity in detecting GC when used in LCI compared with WLI mode. Moreover, the sensitivity of CADe using LCI is significantly higher than those of expert endoscopists using LCI to detect GC.
食管胃十二指肠镜检查是检测胃癌（GC）的最重要工具。在本研究中，我们开发了一种计算机辅助检测（CADe）系统，用于在白光成像（WLI）和联动彩色成像（LCI）模式下检测胃癌，并旨在比较CADe与内镜医师的性能。
该系统基于深度学习框架，利用2017年至2020年间385例患者的9021张图像开发而成。使用2017年至2023年间110例患者的116个LCI和WLI视频来评估每例敏感性和每帧特异性。
CADe在检测胃癌时，置信水平为0.5时，WLI的每例敏感性和每帧特异性分别为78.6%和93.4%，LCI的分别为94.0%和93.3%（p < 0.001）。非专家内镜医师对WLI和LCI的每例敏感性分别为45.8%和80.4%，而专家内镜医师的分别为66.7%和90.6%。关于CADe与内镜医师之间的可检测性，CADe中WLI和LCI的每例敏感性分别为78.6%和94.0%，显著高于专家中LCI的（90.6%，p = 0.004）以及非专家中WLI和LCI的（分别为45.8%和80.4%，p < 0.001）；然而，CADe与专家之间在WLI方面未观察到显著差异（p = 0.134）。
与WLI模式相比，我们的CADe系统在LCI模式下检测胃癌时显示出显著更高的敏感性。此外，使用LCI的CADe的敏感性显著高于使用LCI检测胃癌的专家内镜医师的敏感性。
