我们的研究小组之前建立了一个基于深度学习的临床决策支持系统（CDSS），用于基于内窥镜的胃肿瘤的实时检测和分类。然而，没有考虑到萎缩和肠化生 (IM) 等癌前条件，也没有建立对胃癌发生的所有阶段进行分类的模型。本研究旨在建立并验证适用于所有胃癌患者的实时内窥镜检查的 CDSS胃癌发生的各个阶段，包括萎缩和IM。总共使用了11,868张内窥镜图像进行训练和内部测试。主要结果是分割模型的病变分类准确性（6类：晚期胃癌、早期胃癌、不典型增生、萎缩、IM和正常）以及萎缩和IM病变分割率。进行了以下测试来验证病变分类准确性的性能：（1）使用来自另一机构的 1282 个图像进行外部测试，以及（2）前瞻性地评估现实世界程序中萎缩和 IM 的分类准确性。为了评估临床效用，邀请了 2 位经验丰富的内窥镜医师使用相同的数据集进行盲测。将建立的6级病灶分类模型和癌前病灶分割模型与之前建立的病灶检测模型相结合，构建CDSS。总体病灶分类准确率（95% CI）为90.3%（89%-91.6%）。内部测试。对于性能验证，CDSS 的总体准确率达到 85.3% (83.4%-97.2%)。萎缩和 IM 的每类外部测试准确率分别为 95.3% (92.6%-98%) 和 89.3% (85.4%-93.2%)。在 522 次连续筛查内窥镜检查的实际应用中，CDSS 辅助内窥镜检查显示萎缩的准确性为 92.1%（88.8%-95.4%），IM 的准确性为 95.5%（92%-99%）。在前瞻性真实临床评估中，受邀内镜医师与建立的 CDSS 之间的总体准确性没有显着差异（P=.23）。 CDSS在内部测试中显示，萎缩或IM病变分割的分割率为93.4%（95% CI 92.4%-94.4%）。CDSS在胃癌各阶段的计算机辅助诊断方面取得了较高的性能，并证明了现实世界的应用潜力。©Eun Jeong Kong、Chang Seok Bang、Jae Jun Lee、Hae Min Jeong、Gwang Ho Baik、Jae Hoon Jeong、Sigmund Dick、Gi Hun Lee。最初发表于《医学互联网研究杂志》(https://www.jmir.org)，2023 年 10 月 30 日。

Our research group previously established a deep-learning-based clinical decision support system (CDSS) for real-time endoscopy-based detection and classification of gastric neoplasms. However, preneoplastic conditions, such as atrophy and intestinal metaplasia (IM) were not taken into account, and there is no established model that classifies all stages of gastric carcinogenesis.This study aims to build and validate a CDSS for real-time endoscopy for all stages of gastric carcinogenesis, including atrophy and IM.A total of 11,868 endoscopic images were used for training and internal testing. The primary outcomes were lesion classification accuracy (6 classes: advanced gastric cancer, early gastric cancer, dysplasia, atrophy, IM, and normal) and atrophy and IM lesion segmentation rates for the segmentation model. The following tests were carried out to validate the performance of lesion classification accuracy: (1) external testing using 1282 images from another institution and (2) evaluation of the classification accuracy of atrophy and IM in real-world procedures in a prospective manner. To estimate the clinical utility, 2 experienced endoscopists were invited to perform a blind test with the same data set. A CDSS was constructed by combining the established 6-class lesion classification model and the preneoplastic lesion segmentation model with the previously established lesion detection model.The overall lesion classification accuracy (95% CI) was 90.3% (89%-91.6%) in the internal test. For the performance validation, the CDSS achieved 85.3% (83.4%-97.2%) overall accuracy. The per-class external test accuracies for atrophy and IM were 95.3% (92.6%-98%) and 89.3% (85.4%-93.2%), respectively. CDSS-assisted endoscopy showed an accuracy of 92.1% (88.8%-95.4%) for atrophy and 95.5% (92%-99%) for IM in the real-world application of 522 consecutive screening endoscopies. There was no significant difference in the overall accuracy between the invited endoscopists and established CDSS in the prospective real-clinic evaluation (P=.23). The CDSS demonstrated a segmentation rate of 93.4% (95% CI 92.4%-94.4%) for atrophy or IM lesion segmentation in the internal testing.The CDSS achieved high performance in terms of computer-aided diagnosis of all stages of gastric carcinogenesis and demonstrated real-world application potential.©Eun Jeong Gong, Chang Seok Bang, Jae Jun Lee, Hae Min Jeong, Gwang Ho Baik, Jae Hoon Jeong, Sigmund Dick, Gi Hun Lee. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 30.10.2023.