Background and Aims

Capsule endoscopy (CE) is an important modality for diagnosis and follow-up of Crohn's disease (CD). The severity of ulcers at endoscopy is significant for predicting the course of CD. Deep learning has been proven accurate in detecting ulcers on CE. However, endoscopic classification of ulcers by deep learning has not been attempted. The aim of our study was to develop a deep learning algorithm for automated grading of CD ulcers on CE.

Methods

We retrospectively collected CE images of CD ulcers from our CE database. In experiment 1, the severity of each ulcer was graded by 2 capsule readers based on the PillCam CD classification (grades 1-3 from mild to severe), and the inter-reader variability was evaluated. In experiment 2, a consensus reading by 3 capsule readers was used to train an ordinal convolutional neural network (CNN) to automatically grade images of ulcers, and the resulting algorithm was tested against the consensus reading. A pretraining stage included training the network on images of normal mucosa and ulcerated mucosa.

Results

Overall, our dataset included 17,640 CE images from 49 patients; 7391 images with mucosal ulcers and 10,249 normal images. A total of 2598 randomly selected pathologic images were further graded from 1 to 3 according to ulcer severity in the 2 different experiments. In experiment 1, overall inter-reader agreement occurred for 31% of the images (345 of 1108) and 76% (752 of 989) for distinction of grades 1 and 3. In experiment 2, the algorithm was trained on 1242 images. It achieved an overall agreement for consensus reading of 67% (166 of 248) and 91% (158 of 173) for distinction of grades 1 and 3. The classification accuracy of the algorithm was 0.91 (95% confidence interval, 0.867-0.954) for grade 1 versus grade 3 ulcers, 0.78 (95% confidence interval, 0.716-0.844) for grade 2 versus grade 3, and 0.624 (95% confidence interval, 0.547-0.701) for grade 1 versus grade 2.

Conclusions

CNN achieved high accuracy in detecting severe CD ulcerations. CNN-assisted CE readings in patients with CD can potentially facilitate and improve diagnosis and monitoring in these patients.

中文翻译：

---

克罗恩病患者视频胶囊图像中溃疡严重程度分级：一种序数神经网络解决方案。

背景和目标

胶囊内窥镜检查（CE）是克罗恩病（CD）的诊断和随访的重要手段。内镜下溃疡的严重程度对于预测CD病程很重要。事实证明，深度学习可以准确地发现CE上的溃疡。然而，尚未尝试通过深度学习对溃疡进行内窥镜分类。我们研究的目的是开发一种用于在CE上对CD溃疡进行自动分级的深度学习算法。

方法

我们从我们的CE数据库中回顾性收集了CD溃疡的CE图像。在实验1中，每个溃疡的严重程度由2个胶囊读取器根据PillCam CD分类（从轻度到重度1-3级）进行分级，并评估读取器之间的变异性。在实验2中，使用3个胶囊读取器的共识读数来训练有序卷积神经网络（CNN）以自动对溃疡图像进行评分，并针对共识读数测试了所得算法。预训练阶段包括在正常黏膜和溃疡性黏膜图像上训练网络。

结果

总体而言，我们的数据集包括来自49位患者的17,640张CE图像；有粘膜溃疡的7391张图像和10,249张正常图像。在2个不同的实验中，根据溃疡的严重程度，将总共2598个随机选择的病理图像从1级进一步分级为3级。在实验1中，为区分1级和3级，在31％的图像（1108中的345）和76％（989的752）中发生了总体读者间一致性，在实验2中，该算法在1242张图像上进行了训练。它获得了共识读数的总体一致性，分别为1级和3级，分别为67％（248个中的166个）和91％（173个中的158个）。算法的分类精度为0.91（95％置信区间，0.867-0.954） 1级与3级溃疡比较，2级与3级比较为0.78（95％置信区间，0.716-0.844），3级与0.624（95％置信区间，0.547-0）。

结论

CNN在检测严重CD溃疡方面取得了很高的准确性。CNN辅助的CD患者的CE读数可以潜在地促进和改善这些患者的诊断和监测。