Hamada Kenta, Kawahara Yoshiro, Tanimoto Takayoshi, Ohto Akimitsu, Toda Akira, Aida Toshiaki, Yamasaki Yasushi, Gotoda Tatsuhiro, Ogawa Taiji, Abe Makoto, Okanoue Shotaro, Takei Kensuke, Kikuchi Satoru, Kuroda Shinji, Fujiwara Toshiyoshi, Okada Hiroyuki
Department of Endoscopy, Okayama University Hospital, Okayama, Japan.
Department of Practical Gastrointestinal Endoscopy, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan.
J Gastroenterol Hepatol. 2022 Feb;37(2):352-357. doi: 10.1111/jgh.15725. Epub 2021 Nov 25.
Recently, artificial intelligence (AI) has been used in endoscopic examination and is expected to help in endoscopic diagnosis. We evaluated the feasibility of AI using convolutional neural network (CNN) systems for evaluating the depth of invasion of early gastric cancer (EGC), based on endoscopic images.
This study used a deep CNN model, ResNet152. From patients who underwent treatment for EGC at our hospital between January 2012 and December 2016, we selected 100 consecutive patients with mucosal (M) cancers and 100 consecutive patients with cancers invading the submucosa (SM cancers). A total of 3508 non-magnifying endoscopic images of EGCs, including white-light imaging, linked color imaging, blue laser imaging-bright, and indigo-carmine dye contrast imaging, were included in this study. A total of 2288 images from 132 patients served as the development dataset, and 1220 images from 68 patients served as the testing dataset. Invasion depth was evaluated for each image and lesion. The majority vote was applied to lesion-based evaluation.
The sensitivity, specificity, and accuracy for diagnosing M cancer were 84.9% (95% confidence interval [CI] 82.3%-87.5%), 70.7% (95% CI 66.8%-74.6%), and 78.9% (95% CI 76.6%-81.2%), respectively, for image-based evaluation, and 85.3% (95% CI 73.4%-97.2%), 82.4% (95% CI 69.5%-95.2%), and 83.8% (95% CI 75.1%-92.6%), respectively, for lesion-based evaluation.
The application of AI using CNN to evaluate the depth of invasion of EGCs based on endoscopic images is feasible, and it is worth investing more effort to put this new technology into practical use.
近年来，人工智能（AI）已应用于内镜检查，有望助力内镜诊断。我们基于内镜图像评估了使用卷积神经网络（CNN）系统的人工智能在评估早期胃癌（EGC）浸润深度方面的可行性。
本研究使用深度CNN模型ResNet152。从2012年1月至2016年12月在我院接受EGC治疗的患者中，我们连续选取了100例黏膜（M）癌患者和100例侵犯黏膜下层的癌患者（SM癌患者）。本研究共纳入3508张EGC的非放大内镜图像，包括白光成像、联动彩色成像、蓝光成像-明亮模式以及靛胭脂染色对比成像。来自132例患者的共2288张图像用作开发数据集，来自68例患者的1220张图像用作测试数据集。对每张图像和病变进行浸润深度评估。基于病变的评估采用多数投票法。
基于图像评估，诊断M癌的敏感性、特异性和准确性分别为84.9%（95%置信区间[CI] 82.3%-87.5%）、70.7%（95% CI 66.8%-74.6%）和78.9%（95% CI 76.6%-81.2%）；基于病变评估，诊断M癌的敏感性、特异性和准确性分别为85.3%（95% CI 73.4%-97.2%）、82.4%（95% CI 69.5%-95.2%）和83.8%（95% CI 75.1%-92.6%）。
使用CNN的人工智能基于内镜图像评估EGC浸润深度是可行的，值得投入更多努力将这项新技术投入实际应用。
