Development of an automated tool for the estimation of histological remission in ulcerative colitis using single wavelength endoscopy technology

Abstract

Introduction: Ulcerative colitis (UC) management employs a strategy targeting histological and endoscopic remission. Correlation of white-light endoscopy (WLE) scores with histological activity is limited. Single-wavelength endoscopy (SWE) addressing microvascular changes reflecting histological disease activity, may better assess histological remission.

Aims and methods: Our goal was to assess the accuracy of a computer-aided diagnosis (CAD) system for histological activity estimation in UC, based on either WLE or SWE. We collected 6926 sets of corresponding WLE and SWE frames in 112 patients with UC, using a prototype endoscopic system enabling both imaging methods (FUJIFILM, Tokyo, Japan). Histological remission (Geboes score ≤2B.0) assessed at the location of imaging was annotated for all frames and separate WLE-CAD and SWE-CAD models were trained using deep learning for automated detection of histological remission with either imaging modality.

Results: Initial training of both models on the same subset of 42 patients, resulted in SWE-CAD outperforming WLE-CAD with a mean sensitivity of 88.0% vs 73.9% (p < 0.001), a mean specificity of 71.7% vs 65.6% (p=0.45), and a diagnostic accuracy of 83.3% vs 67.5% (p<0.005), respectively. Further training of the SWE-CAD model on the entire dataset of 112 patients resulted in SWE-CAD achieving a 95.2% accuracy, 96.4% sensitivity, and 92.9% specificity on a section level.

Conclusion: By utilizing automated CAD based on non-magnifying SWE for enhanced capillary visibility versus WLE, histological remission was detected with 95.2% diagnostic accuracy in patients with UC, offering stable objectivity and helping to exclude inter-reader variability.

Keywords: Deep learning; Endoscopy; Histology; Ulcerative Colitis.