Department of Internal Medicine and Institute of Gastroenterology, Yonsei University College of Medicine, Seoul, Republic of Korea.
Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Republic of Korea.
J Gastroenterol Hepatol. 2021 Aug;36(8):2141-2148. doi: 10.1111/jgh.15433. Epub 2021 Feb 20.
Pattern analysis of big data can provide a superior direction for the clinical differentiation of diseases with similar endoscopic findings. This study aimed to develop a deep-learning algorithm that performs differential diagnosis between intestinal Behçet's disease (BD), Crohn's disease (CD), and intestinal tuberculosis (ITB) using colonoscopy images.
The typical pattern for each disease was defined as a typical image. We implemented a convolutional neural network (CNN) using Pytorch and visualized a deep-learning model through Gradient-weighted Class Activation Mapping. The performance of the algorithm was evaluated using the area under the receiver operating characteristic curve (AUROC).
A total of 6617 colonoscopy images of 211 CD, 299 intestinal BD, and 217 ITB patients were used. The accuracy of the algorithm for discriminating the three diseases (all-images: 65.15% vs typical images: 72.01%, P = 0.024) and discriminating between intestinal BD and CD (all-images: 78.15% vs typical images: 85.62%, P = 0.010) was significantly different between all-images and typical images. The CNN clearly differentiated colonoscopy images of the diseases (AUROC from 0.7846 to 0.8586). Algorithmic prediction AUROC for typical images ranged from 0.8211 to 0.9360.
This study found that a deep-learning model can discriminate between colonoscopy images of intestinal BD, CD, and ITB. In particular, the algorithm demonstrated superior discrimination ability for typical images. This approach presents a beneficial method for the differential diagnosis of the diseases.
大数据模式分析可为内镜表现相似的疾病的临床鉴别提供更好的方向。本研究旨在开发一种深度学习算法，使用结肠镜图像对肠贝赫切特病（BD）、克罗恩病（CD）和肠结核（ITB）进行鉴别诊断。
将每种疾病的典型模式定义为典型图像。我们使用 Pytorch 实现了卷积神经网络（CNN），并通过 Gradient-weighted Class Activation Mapping 对深度学习模型进行可视化。使用接收者操作特征曲线下的面积（AUROC）评估算法的性能。
共纳入 211 例 CD、299 例肠 BD 和 217 例 ITB 患者的 6617 张结肠镜图像。该算法对三种疾病的鉴别（全图像：65.15% vs 典型图像：72.01%，P=0.024）和肠 BD 与 CD 的鉴别（全图像：78.15% vs 典型图像：85.62%，P=0.010）的准确率在全图像和典型图像之间存在显著差异。CNN 清晰地区分了疾病的结肠镜图像（AUROC 范围为 0.7846 至 0.8586）。典型图像的算法预测 AUROC 范围为 0.8211 至 0.9360。
本研究发现，深度学习模型可区分肠 BD、CD 和 ITB 的结肠镜图像。特别是，该算法对典型图像具有较好的鉴别能力。这种方法为这些疾病的鉴别诊断提供了有益的方法。
