Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
Ankon Technologies (Wuhan) Co., Ltd, Wuhan, China.
Endoscopy. 2023 Jan;55(1):44-51. doi: 10.1055/a-1881-4209. Epub 2022 Aug 5.
Further development of deep learning-based artificial intelligence (AI) technology to automatically diagnose multiple abnormalities in small-bowel capsule endoscopy (SBCE) videos is necessary. We aimed to develop an AI model, to compare its diagnostic performance with doctors of different experience levels, and to further evaluate its auxiliary role for doctors in diagnosing multiple abnormalities in SBCE videos. METHODS : The AI model was trained using 280 426 images from 2565 patients, and the diagnostic performance was validated in 240 videos. RESULTS : The sensitivity of the AI model for red spots, inflammation, blood content, vascular lesions, protruding lesions, parasites, diverticulum, and normal variants was 97.8 %, 96.1 %, 96.1 %, 94.7 %, 95.6 %, 100 %, 100 %, and 96.4 %, respectively. The specificity was 86.0 %, 75.3 %, 87.3 %, 77.8 %, 67.7 %, 97.5 %, 91.2 %, and 81.3 %, respectively. The accuracy was 95.0 %, 88.8 %, 89.2 %, 79.2 %, 80.8 %, 97.5 %, 91.3 %, and 93.3 %, respectively. For junior doctors, the assistance of the AI model increased the overall accuracy from 85.5 % to 97.9 % ( < 0.001, Bonferroni corrected), comparable to that of experts (96.6 %, > 0.0125, Bonferroni corrected). CONCLUSIONS : This well-trained AI diagnostic model automatically diagnosed multiple small-bowel abnormalities simultaneously based on video-level recognition, with potential as an excellent auxiliary system for less-experienced endoscopists.
为了自动诊断小肠胶囊内镜（SBCE）视频中的多种异常，需要进一步开发基于深度学习的人工智能（AI）技术。我们旨在开发一种 AI 模型，比较其与不同经验水平医生的诊断性能，并进一步评估其在诊断 SBCE 视频中多种异常方面对医生的辅助作用。
使用来自 2565 名患者的 280426 张图像对 AI 模型进行训练，并在 240 个视频中验证其诊断性能。
AI 模型对红点、炎症、血液内容物、血管病变、突出病变、寄生虫、憩室和正常变异的敏感度分别为 97.8%、96.1%、96.1%、94.7%、95.6%、100%、100%和 96.4%。特异性分别为 86.0%、75.3%、87.3%、77.8%、67.7%、97.5%、91.2%和 81.3%。准确性分别为 95.0%、88.8%、89.2%、79.2%、80.8%、97.5%、91.3%和 93.3%。对于初级医生来说，AI 模型的辅助作用将整体准确率从 85.5%提高到 97.9%（ < 0.001，Bonferroni 校正），与专家相当（96.6%， > 0.0125，Bonferroni 校正）。
该训练有素的 AI 诊断模型可基于视频级识别自动同时诊断多种小肠异常，具有成为经验不足的内镜医生优秀辅助系统的潜力。
