Automatic Detection of Bowel Disease with Residual Networks

TL;DR

This paper investigates the use of deep residual networks for detecting Crohn's disease in MRI images, demonstrating comparable accuracy to clinical standards with faster processing and improved interpretability.

Contribution

It introduces a deep learning approach using residual networks for Crohn's disease detection in MRI, highlighting efficiency and interpretability improvements over existing methods.

Findings

Deep learning achieves comparable performance to MaRIA score.

Residual networks reduce inference time significantly.

Soft attention enhances interpretability of the model.

Abstract

Crohn's disease, one of two inflammatory bowel diseases (IBD), affects 200,000 people in the UK alone, or roughly one in every 500. We explore the feasibility of deep learning algorithms for identification of terminal ileal Crohn's disease in Magnetic Resonance Enterography images on a small dataset. We show that they provide comparable performance to the current clinical standard, the MaRIA score, while requiring only a fraction of the preparation and inference time. Moreover, bowels are subject to high variation between individuals due to the complex and free-moving anatomy. Thus we also explore the effect of difficulty of the classification at hand on performance. Finally, we employ soft attention mechanisms to amplify salient local features and add interpretability.