Arges: Spatio-Temporal Transformer for Ulcerative Colitis Severity Assessment in Endoscopy Videos

TL;DR

Arges introduces a spatio-temporal transformer model that automates ulcerative colitis severity assessment from endoscopy videos, outperforming existing methods and generalizing well across datasets.

Contribution

The paper presents Arges, a novel transformer-based framework utilizing a foundation model and spatio-temporal encoding for accurate, automated UC severity scoring from endoscopy videos.

Findings

F1 score for MES increased by 4.1% over state-of-the-art.

Significant improvements in UCEIS component scores.

Model generalizes successfully to unseen clinical trial data.

Abstract

Accurate assessment of disease severity from endoscopy videos in ulcerative colitis (UC) is crucial for evaluating drug efficacy in clinical trials. Severity is often measured by the Mayo Endoscopic Subscore (MES) and Ulcerative Colitis Endoscopic Index of Severity (UCEIS) score. However, expert MES/UCEIS annotation is time-consuming and susceptible to inter-rater variability, factors addressable by automation. Automation attempts with frame-level labels face challenges in fully-supervised solutions due to the prevalence of video-level labels in clinical trials. CNN-based weakly-supervised models (WSL) with end-to-end (e2e) training lack generalization to new disease scores and ignore spatio-temporal information crucial for accurate scoring. To address these limitations, we propose "Arges", a deep learning framework that utilizes a transformer with positional encoding to incorporate spatio-temporal information from frame features to estimate disease severity scores in endoscopy video. Extracted features are derived from a foundation model (ArgesFM), pre-trained on a large diverse dataset from multiple clinical trials (61M frames, 3927 videos). We evaluate four UC disease severity scores, including MES and three UCEIS component scores. Test set evaluation indicates significant improvements, with F1 scores increasing by 4.1% for MES and 18.8%, 6.6%, 3.8% for the three UCEIS component scores compared to state-of-the-art methods. Prospective validation on previously unseen clinical trial data further demonstrates the model's successful generalization.