Patch-level instance-group discrimination with pretext-invariant learning for colitis scoring

TL;DR

This paper introduces a novel self-supervised learning method, PLD-PIRL, that improves the accuracy and robustness of endoscopic ulcerative colitis grading by detecting subtle mucosal inflammation changes.

Contribution

The paper proposes a new patch-level instance-group discrimination method with pretext-invariant learning for better IBD endoscopic image analysis.

Findings

4.75% accuracy improvement on test data

6.64% accuracy improvement on unseen data

Enhanced robustness over existing SSL methods

Abstract

Inflammatory bowel disease (IBD), in particular ulcerative colitis (UC), is graded by endoscopists and this assessment is the basis for risk stratification and therapy monitoring. Presently, endoscopic characterisation is largely operator dependant leading to sometimes undesirable clinical outcomes for patients with IBD. We focus on the Mayo Endoscopic Scoring (MES) system which is widely used but requires the reliable identification of subtle changes in mucosal inflammation. Most existing deep learning classification methods cannot detect these fine-grained changes which make UC grading such a challenging task. In this work, we introduce a novel patch-level instance-group discrimination with pretext-invariant representation learning (PLD-PIRL) for self-supervised learning (SSL). Our experiments demonstrate both improved accuracy and robustness compared to the baseline supervised network and several state-of-the-art SSL methods. Compared to the baseline (ResNet50) supervised classification our proposed PLD-PIRL obtained an improvement of 4.75% on hold-out test data and 6.64% on unseen center test data for top-1 accuracy.