文献速递炎症性肠病消化内镜

克罗恩病患者胶囊内镜图像中溃疡严重程度分级:一种有序神经网络解决方案

Ulcer severity grading in video capsule images of patients with Crohn's disease: an ordinal neural network solution.
PubMed 文献 · Gastrointest Endosc · 2020-06-12

该研究回顾性收集49例克罗恩病患者的17640幅胶囊内镜图像,由2名读片者按PillCam CD分类(1-3级)评估溃疡严重程度,并训练有序卷积神经网络自动分级。算法对1级与3级溃疡的区分准确率达0.91(95%CI 0.867-0.954),与共识读片总体一致率为67%(166/248),对1级与3级区分一致率为91%(158/173)。作者认为卷积神经网络在检测严重克罗恩病溃疡方面达到高准确率,可能有助于改善诊断和监测。

要点

  • 研究纳入49例患者的17640幅胶囊内镜图像,其中7391幅有黏膜溃疡、10249幅正常。
  • 算法对1级与3级溃疡分类准确率为0.91(95%CI 0.867-0.954),对2级与3级为0.78(95%CI 0.716-0.844),对1级与2级为0.624(95%CI 0.547-0.701)。
  • 算法与3名读片者共识读片的总体一致率为67%(166/248),对1级与3级区分一致率为91%(158/173)。

核心结论

  • 卷积神经网络在检测严重克罗恩病溃疡方面达到高准确率。
  • 卷积神经网络辅助的胶囊内镜读片可能有助于促进和改善克罗恩病患者的诊断与监测。

研究设计与样本

  • 回顾性收集本中心胶囊内镜数据库中克罗恩病溃疡的胶囊内镜图像。
  • 实验1由2名胶囊读片者按PillCam CD分类(1-3级,从轻到重)对每处溃疡的严重程度分级,并评估读片者间变异。
  • 实验2由3名胶囊读片者的共识读片用于训练有序卷积神经网络自动分级溃疡图像,并与共识读片进行测试对比。
  • 预训练阶段包括在正常黏膜和溃疡黏膜图像上训练网络。
  • 数据集共纳入49例患者的17640幅胶囊内镜图像,其中7391幅有黏膜溃疡、10249幅正常;随机选取2598幅病理图像在两个实验中按溃疡严重程度进一步分为1-3级。

主要发现

  • 实验1中,读片者间总体一致率为31%(345/1108),对1级与3级区分的一致率为76%(752/989)。
  • 实验2中,算法在1242幅图像上训练,与共识读片的总体一致率为67%(166/248),对1级与3级区分的一致率为91%(158/173)。
  • 算法对1级与3级溃疡的分类准确率为0.91(95%CI 0.867-0.954),对2级与3级为0.78(95%CI 0.716-0.844),对1级与2级为0.624(95%CI 0.547-0.701)。

关键数值与推荐

  • 溃疡严重程度按PillCam CD分类分为1-3级(从轻到重)。
  • 算法对1级与3级溃疡分类准确率为0.91(95%CI 0.867-0.954)。
  • 算法对2级与3级溃疡分类准确率为0.78(95%CI 0.716-0.844)。
  • 算法对1级与2级溃疡分类准确率为0.624(95%CI 0.547-0.701)。

临床怎么用

  • 原文未据此给出临床推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

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.

来源:Gastrointest Endosc,查看原文。版权归原作者所有。

引用

  1. Barash Y, Azaria L, Soffer S, et al. Ulcer severity grading in video capsule images of patients with Crohn's disease: an ordinal neural network solution. Gastrointest Endosc. 2020. PMID: 32535191. doi:10.1016/j.gie.2020.05.066

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。