Predicting mucosal healing in Crohn's disease: development of a deep-learning model based on intestinal ultrasound images

Abstract

Objective: Predicting treatment response in Crohn's disease (CD) is essential for making an optimal therapeutic regimen, but relevant models are lacking. This study aimed to develop a deep learning model based on baseline intestinal ultrasound (IUS) images and clinical information to predict mucosal healing.

Methods: Consecutive CD patients who underwent pretreatment IUS were retrospectively recruited at a tertiary hospital. A total of 1548 IUS images of longitudinal diseased bowel segments were collected and divided into a training cohort and a test cohort. A convolutional neural network model was developed to predict mucosal healing after one year of standardized treatment. The model's efficacy was validated using the five-fold internal cross-validation and further tested in the test cohort.

Results: A total of 190 patients (68.9% men, mean age 32.3 ± 14.1 years) were enrolled, consisting of 1038 IUS images of mucosal healing and 510 images of no mucosal healing. The mean area under the curve in the test cohort was 0.73 (95% CI: 0.68-0.78), with the mean sensitivity of 68.1% (95% CI: 60.5-77.4%), specificity of 69.5% (95% CI: 60.1-77.2%), positive prediction value of 80.0% (95% CI: 74.5-84.9%), negative prediction value of 54.8% (95% CI: 48.0-63.7%). Heat maps showing the deep-learning decision-making process revealed that information from the bowel wall, serous surface, and surrounding mesentery was mainly considered by the model.

Conclusions: We developed a deep learning model based on IUS images to predict mucosal healing in CD with notable accuracy. Further validation and improvement of this model with more multi-center, real-world data are needed.

Critical relevance statement: Predicting treatment response in CD is essential to making an optimal therapeutic regimen. In this study, a deep-learning model using pretreatment ultrasound images and clinical information was generated to predict mucosal healing with an AUC of 0.73.

Key points: Response to medication treatment is highly variable among patients with CD. High-resolution IUS images of the intestinal wall may hide significant characteristics for treatment response. A deep-learning model capable of predicting treatment response was generated using pretreatment IUS images.

Keywords: Crohn’s disease; Deep learning; Intestinal ultrasound.; Outcome prediction.

Fig. 1

A flow diagram describing patient enrollment. CD, Crohn’s disease; IUS, intestinal ultrasound

Fig. 2

Scheme of a CNN. A A flowchart of the CNN model workflow. The model consists of three parts: the IUS image feature extraction part with an SE module, the IUS image and tabular data fusion part, and the classifier part. B A SE structure diagram. Input is the rough feature map collected from the previous step, and output is the new feature map scaled after the Sigmoid activation function, which calculates the weight coefficient of each channel. IUS, intestinal ultrasound; CDAI, Crohn’s disease activity index; FC, full connection; ReLU, rectified linear unit, one activation function

Fig. 3

ROC curve of the CNN model

Fig. 4

Applying Grad-CAM to improve interpretability. A, C IUS images; B, D the corresponding heat maps calculated by the Grad-CAM method, with warmer colors indicating regions activated by the CNN model with larger predictive significance, and colder colors indicating regions with less predictive significance. Grad-CAM, gradient-weighted class activation mapping