Takabayashi Kaoru, Kobayashi Taku, Matsuoka Katsuyoshi, Levesque Barrett G, Kawamura Takuji, Tanaka Kiyohito, Kadota Takeaki, Bise Ryoma, Uchida Seiichi, Kanai Takanori, Ogata Haruhiko
Center for Diagnostic and Therapeutic Endoscopy, Keio University School of Medicine, Tokyo, Japan.
Center for Advanced IBD Research and Treatment, Kitasato University Kitasato Institute Hospital, Tokyo, Japan.
Dig Endosc. 2024 May;36(5):582-590. doi: 10.1111/den.14677. Epub 2023 Oct 11.
Existing endoscopic scores for ulcerative colitis (UC) objectively categorize disease severity based on the presence or absence of endoscopic findings; therefore, it may not reflect the range of clinical severity within each category. However, inflammatory bowel disease (IBD) expert endoscopists categorize the severity and diagnose the overall impression of the degree of inflammation. This study aimed to develop an artificial intelligence (AI) system that can accurately represent the assessment of the endoscopic severity of UC by IBD expert endoscopists.
A ranking-convolutional neural network (ranking-CNN) was trained using comparative information on the UC severity of 13,826 pairs of endoscopic images created by IBD expert endoscopists. Using the trained ranking-CNN, the UC Endoscopic Gradation Scale (UCEGS) was used to express severity. Correlation coefficients were calculated to ensure that there were no inconsistencies in assessments of severity made using UCEGS diagnosed by the AI and the Mayo Endoscopic Subscore, and the correlation coefficients of the mean for test images assessed using UCEGS by four IBD expert endoscopists and the AI.
Spearman's correlation coefficient between the UCEGS diagnosed by AI and Mayo Endoscopic Subscore was approximately 0.89. The correlation coefficients between IBD expert endoscopists and the AI of the evaluation results were all higher than 0.95 (P < 0.01).
The AI developed here can diagnose UC severity endoscopically similar to IBD expert endoscopists.
现有的溃疡性结肠炎（UC）内镜评分基于内镜检查结果的有无对疾病严重程度进行客观分类；因此，它可能无法反映每个类别内临床严重程度的范围。然而，炎症性肠病（IBD）专家内镜医师会对严重程度进行分类并诊断炎症程度的总体印象。本研究旨在开发一种人工智能（AI）系统，该系统能够准确呈现IBD专家内镜医师对UC内镜严重程度的评估。
使用IBD专家内镜医师创建的13826对内镜图像的UC严重程度比较信息训练排名卷积神经网络（ranking-CNN）。使用训练好的ranking-CNN，用UC内镜分级量表（UCEGS）来表示严重程度。计算相关系数，以确保使用人工智能诊断的UCEGS和梅奥内镜子评分对严重程度的评估不存在不一致，以及四位IBD专家内镜医师和人工智能使用UCEGS评估的测试图像平均值的相关系数。
人工智能诊断的UCEGS与梅奥内镜子评分之间的Spearman相关系数约为0.89。IBD专家内镜医师与人工智能评估结果的相关系数均高于0.95（P<0.01）。
此处开发的人工智能在内镜下诊断UC严重程度的能力与IBD专家内镜医师相似。
