Li Jia, Zhu Yijie, Dong Zehua, He Xinqi, Xu Ming, Liu Jun, Zhang Mengjiao, Tao Xiao, Du Hongliu, Chen Di, Huang Li, Shang Renduo, Zhang Lihui, Luo Renquan, Zhou Wei, Deng Yunchao, Huang Xu, Li Yanxia, Chen Boru, Gong Rongrong, Zhang Chenxia, Li Xun, Wu Lianlian, Yu Honggang
Department of Gastroenterology, Renmin Hospital of Wuhan University, 99 Zhangzhidong Road, Wuhan, Hubei 430060, PR China.
Hubei Key Laboratory of Digestive System, Renmin Hospital of Wuhan University, Wuhan, Hubei 430060, PR China.
EClinicalMedicine. 2022 Mar 30;46:101366. doi: 10.1016/j.eclinm.2022.101366. eCollection 2022 Apr.
Prompt diagnosis of early gastric cancer (EGC) is crucial for improving patient survival. However, most previous computer-aided-diagnosis (CAD) systems did not concretize or explain diagnostic theories. We aimed to develop a logical anthropomorphic artificial intelligence (AI) diagnostic system named ENDOANGEL-LA (logical anthropomorphic) for EGCs under magnifying image enhanced endoscopy (M-IEE).
We retrospectively collected data for 692 patients and 1897 images from Renmin Hospital of Wuhan University, Wuhan, China between Nov 15, 2016 and May 7, 2019. The images were randomly assigned to the training set and test set by patient with a ratio of about 4:1. ENDOANGEL-LA was developed based on feature extraction combining quantitative analysis, deep learning (DL), and machine learning (ML). 11 diagnostic feature indexes were integrated into seven ML models, and an optimal model was selected. The performance of ENDOANGEL-LA was evaluated and compared with endoscopists and sole DL models. The satisfaction of endoscopists on ENDOANGEL-LA and sole DL model was also compared.
Random forest showed the best performance, and demarcation line and microstructures density were the most important feature indexes. The accuracy of ENDOANGEL-LA in images (88.76%) was significantly higher than that of sole DL model (82.77%, = 0.034) and the novices (71.63%, <0.001), and comparable to that of the experts (88.95%). The accuracy of ENDOANGEL-LA in videos (87.00%) was significantly higher than that of the sole DL model (68.00%, <0.001), and comparable to that of the endoscopists (89.00%). The accuracy (87.45%, <0.001) of novices with the assistance of ENDOANGEL-LA was significantly improved. The satisfaction of endoscopists on ENDOANGEL-LA was significantly higher than that of sole DL model.
We established a logical anthropomorphic system (ENDOANGEL-LA) that can diagnose EGC under M-IEE with diagnostic theory concretization, high accuracy, and good explainability. It has the potential to increase interactivity between endoscopists and CADs, and improve trust and acceptability of endoscopists for CADs.
This work was partly supported by a grant from the Hubei Province Major Science and Technology Innovation Project (2018-916-000-008) and the Fundamental Research Funds for the Central Universities (2042021kf0084).
早期胃癌（EGC）的及时诊断对于提高患者生存率至关重要。然而，以往大多数计算机辅助诊断（CAD）系统并未将诊断理论具体化或进行解释。我们旨在开发一种名为ENDOANGEL-LA（逻辑拟人化）的逻辑拟人化人工智能（AI）诊断系统，用于在放大图像增强内镜检查（M-IEE）下诊断EGC。
我们回顾性收集了2016年11月15日至2019年5月7日期间武汉大学人民医院692例患者的1897张图像数据。图像按患者随机分配到训练集和测试集，比例约为4:1。ENDOANGEL-LA基于结合定量分析、深度学习（DL）和机器学习（ML）的特征提取开发。将11个诊断特征指标整合到7个ML模型中，并选择了一个最优模型。对ENDOANGEL-LA的性能进行评估，并与内镜医师和单一DL模型进行比较。还比较了内镜医师对ENDOANGEL-LA和单一DL模型的满意度。
随机森林表现最佳，分界线和微结构密度是最重要的特征指标。ENDOANGEL-LA在图像中的准确率（88.76%）显著高于单一DL模型（82.77%，P = 0.034）和新手（71.63%，P<0.001），与专家的准确率（88.95%）相当。ENDOANGEL-LA在视频中的准确率（87.00%）显著高于单一DL模型（68.00%，P<0.001），与内镜医师的准确率（89.00%）相当。在ENDOANGEL-LA辅助下新手的准确率（87.45%，P<0.001）显著提高。内镜医师对ENDOANGEL-LA的满意度显著高于单一DL模型。
我们建立了一个逻辑拟人化系统（ENDOANGEL-LA），它可以在M-IEE下诊断EGC，具有诊断理论具体化、准确率高和可解释性好的特点。它有可能增加内镜医师与CAD之间的互动，并提高内镜医师对CAD的信任度和接受度。
本研究部分得到湖北省重大科技创新项目（2018-916-000-
