Application of artificial intelligence using a convolutional neural network for diagnosis of early gastric cancer based on magnifying endoscopy with narrow-band imaging.
Application of artificial intelligence using a convolutional neural network for diagnosis of early gastric cancer based on magnifying endoscopy with narrow-band imaging.
复制标题
基于卷积神经网络的人工智能在窄带放大内镜早期胃癌诊断中的应用
DOI：
10.1111/jgh.15190
复制
发表时间：
2021-03
影响因子：
4.1
通讯作者：
Tada T
中科院分区：
文献类型：
--
作者：
Ueyama H;Kato Y;Akazawa Y;Yatagai N;Komori H;Takeda T;Matsumoto K;Ueda K;Matsumoto K;Hojo M;Yao T;Nagahara A;Tada T
窄带成像放大内镜（ME-NBI）为临床实践做出了巨大贡献。然而，获得早期胃癌（EGC）的ME-NBI诊断技能需要相当多的专业知识和经验。最近，使用深度学习和卷积神经网络（CNN）的人工智能（AI）在各个医疗领域取得了显着进展。在这里，我们构建了一个基于ME-NBI图像的AI辅助CNN计算机辅助诊断（CAD）系统来诊断EGC，并评估了AI辅助CNN-CAD系统的诊断准确性。AI辅助的CNN-CAD系统（ResNet50）在5574个ME-NBI图像（3797个EGC，1777个非癌粘膜和病变）的数据集上进行了训练和验证。为了评价诊断准确性，使用AI辅助的CNN ‐ CAD系统评估了2300个ME-NBI图像（1430个EGC，870个非癌粘膜和病变）的单独测试数据集。人工智能辅助的CNN-CAD系统需要60秒来分析2300张测试图像。CNN的总体准确性、敏感性、特异性、阳性预测值和阴性预测值分别为98.7%、98%、100%、100%和96.8%。所有误诊的EGC图像均为低质量或表面凹陷和肠型粘膜内癌，即使是经验丰富的内镜医师也难以与胃炎区分。用于EGC的ME-NBI诊断的AI辅助CNN ‐ CAD系统可以在短时间内处理许多存储的ME-NBI图像，具有较高的诊断能力。该系统可能具有很大的潜力，未来应用于真实的临床环境，这可能有助于ME-NBI诊断EGC的实践。
Magnifying endoscopy with narrow‐band imaging (ME‐NBI) has made a huge contribution to clinical practice. However, acquiring skill at ME‐NBI diagnosis of early gastric cancer (EGC) requires considerable expertise and experience. Recently, artificial intelligence (AI), using deep learning and a convolutional neural network (CNN), has made remarkable progress in various medical fields. Here, we constructed an AI‐assisted CNN computer‐aided diagnosis (CAD) system, based on ME‐NBI images, to diagnose EGC and evaluated the diagnostic accuracy of the AI‐assisted CNN‐CAD system. The AI‐assisted CNN‐CAD system (ResNet50) was trained and validated on a dataset of 5574 ME‐NBI images (3797 EGCs, 1777 non‐cancerous mucosa and lesions). To evaluate the diagnostic accuracy, a separate test dataset of 2300 ME‐NBI images (1430 EGCs, 870 non‐cancerous mucosa and lesions) was assessed using the AI‐assisted CNN‐CAD system. The AI‐assisted CNN‐CAD system required 60 s to analyze 2300 test images. The overall accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the CNN were 98.7%, 98%, 100%, 100%, and 96.8%, respectively. All misdiagnosed images of EGCs were of low‐quality or of superficially depressed and intestinal‐type intramucosal cancers that were difficult to distinguish from gastritis, even by experienced endoscopists. The AI‐assisted CNN‐CAD system for ME‐NBI diagnosis of EGC could process many stored ME‐NBI images in a short period of time and had a high diagnostic ability. This system may have great potential for future application to real clinical settings, which could facilitate ME‐NBI diagnosis of EGC in practice.
登录
查看更多内容
对医疗统计信息的自由使用的易于使用的软件“ EZR”的调查。
影响因子：
4.8
作者：
Kanda Y
通讯作者：
Kanda Y
影响因子：
4.6
作者：
Takiyama H;Ozawa T;Ishihara S;Fujishiro M;Shichijo S;Nomura S;Miura M;Tada T
通讯作者：
Tada T
影响因子：
5.6
作者：
Ueyama, Hiroya;Yao, Takashi;Watanabe, Sumio
通讯作者：
Watanabe, Sumio
影响因子：
4.5
作者：
Kodashima, S.;Fujishiro, M.;Omata, M.
通讯作者：
Omata, M.
影响因子：
3.2
作者：
Akazawa, Yoichi;Ueyama, Hiroya;Nagahara, Akihito
通讯作者：
Nagahara, Akihito