Histologic image-based ensemble model to identify myenteric plexitis and predict endoscopic postoperative recurrence in Crohn's disease: a multicentre, retrospective study.

Abstract

Myenteric plexitis is correlated with postoperative recurrence of Crohn's disease when relying on traditional statistical methods. However, comprehensive assessment of the myenteric plexus remains challenging. This study aimed to develop and validate a deep learning system to predict postoperative recurrence through automatic screening and identification of features of the muscular layer and myenteric plexus. In this study, we retrospectively reviewed 205 patients who underwent bowel resection surgery from 2 hospitals. Patients were divided into a training cohort (n=108), an internal validation cohort (n=47) and an external validation cohort (n=50). A total of 190960 patches from 278 whole-slide images of surgical specimens were analysed using ResNet50, and 6144 features were extracted after transfer learning. We used five robust algorithms to construct classification models. The performances of the models were evaluated by the area under the receiver operating characteristic curve in three cohorts. The stacking model achieved satisfactory accuracy in predicting postoperative recurrence of CD in the training cohort (AUC: 0.980; 95% CI 0.960-0.999), internal validation cohort (AUC: 0.908; 95% CI 0.823-0.992), and external validation cohort (AUC: 0.868; 95% CI 0.761-0.975). The accuracy for identifying the severity of myenteric plexitis was 0.833, 0.745, and 0.694 in the training cohort, internal validation cohort and external validation cohort, respectively. Our work initially established an interpretable stacking model based on muscular layer and myenteric plexus features extracted from histologic images to identify the severity of myenteric plexitis and predict postoperative recurrence of CD.