基于内镜超声图像预测胃肠道间质瘤的人工智能：开发、验证及与内镜超声医师的比较

Artificial Intelligence in the Prediction of Gastrointestinal Stromal Tumors on Endoscopic Ultrasonography Images: Development, Validation and Comparison with Endosonographers.

机构信息

Department of Gastrointestinal Endoscopy, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.

Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.

出版信息

Gut Liver. 2023 Nov 15;17(6):874-883. doi: 10.5009/gnl220347. Epub 2023 Jan 26.

DOI:10.5009/gnl220347

PMID:36700302

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10651383/

Abstract

BACKGROUND/AIMS: The accuracy of endosonographers in diagnosing gastric subepithelial lesions (SELs) using endoscopic ultrasonography (EUS) is influenced by experience and subjectivity. Artificial intelligence (AI) has achieved remarkable development in this field. This study aimed to develop an AI-based EUS diagnostic model for the diagnosis of SELs, and evaluated its efficacy with external validation.

METHODS

We developed the EUS-AI model with ResNeSt50 using EUS images from two hospitals to predict the histopathology of the gastric SELs originating from muscularis propria. The diagnostic performance of the model was also validated using EUS images obtained from four other hospitals.

RESULTS

A total of 2,057 images from 367 patients (375 SELs) were chosen to build the models, and 914 images from 106 patients (108 SELs) were chosen for external validation. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the model for differentiating gastrointestinal stromal tumors (GISTs) and non-GISTs in the external validation sets by images were 82.01%, 68.22%, 86.77%, 59.86%, and 78.12%, respectively. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy in the external validation set by tumors were 83.75%, 71.43%, 89.33%, 60.61%, and 80.56%, respectively. The EUS-AI model showed better performance (especially specificity) than some endosonographers. The model helped improve the sensitivity, specificity, and accuracy of certain endosonographers.

CONCLUSIONS

We developed an EUS-AI model to classify gastric SELs originating from muscularis propria into GISTs and non-GISTs with good accuracy. The model may help improve the diagnostic performance of endosonographers. Further work is required to develop a multi-modal EUS-AI system.

摘要

背景/目的：超声内镜（EUS）诊断胃黏膜下病变（SEL）的准确性受经验和主观性的影响。人工智能（AI）在这一领域取得了显著的发展。本研究旨在开发一种基于 AI 的 EUS 诊断模型，用于诊断 SEL，并通过外部验证评估其疗效。

方法

我们使用来自两家医院的 EUS 图像开发了基于 ResNeSt50 的 EUS-AI 模型，用于预测源自固有肌层的胃 SEL 的组织病理学。还使用来自另外四家医院的 EUS 图像验证了模型的诊断性能。

结果

共选择 367 例患者（375 个 SEL）的 2057 张图像来构建模型，选择 106 例患者（108 个 SEL）的 914 张图像进行外部验证。模型在外部验证集中通过图像区分胃肠道间质瘤（GIST）和非 GIST 的灵敏度、特异性、阳性预测值、阴性预测值和准确性分别为 82.01%、68.22%、86.77%、59.86%和 78.12%。在外部验证集中通过肿瘤的灵敏度、特异性、阳性预测值、阴性预测值和准确性分别为 83.75%、71.43%、89.33%、60.61%和 80.56%。EUS-AI 模型的性能（尤其是特异性）优于一些超声内镜医生。该模型有助于提高某些超声内镜医生的敏感性、特异性和准确性。