Weakly Supervised Multicenter Nancy Index Scoring in Ulcerative Colitis Using Foundation Models

TL;DR

This study introduces a weakly supervised multiple instance learning approach utilizing foundation models to automate and improve the accuracy of histological ulcerative colitis activity scoring across multicenter datasets.

Contribution

It presents a novel weakly supervised method that leverages foundation models for multicenter ulcerative colitis histology scoring without dense annotations.

Findings

Foundation model choice and resolution significantly impact performance.

Virchow2 encoder provides the most consistent gains.

Ensembling improves five-grade Nancy histological index prediction.

Abstract

Histologic assessment of ulcerative colitis (UC) activity is an important endpoint in clinical trials and routine care, but manual grading with indices such as the Nancy histological index (NHI) is time-consuming and prone to observer variability. While computational pathology methods can automate scoring, many approaches depend on dense region-level annotations, which are costly to obtain, particularly in heterogeneous, multicenter cohorts. We propose a weakly supervised multiple instance learning (MIL) approach for whole-slide images that learns from case- and slide-level NHI labels, leveraging foundation models. Our method targets clinically relevant endpoints, including neutrophilic activity and derived Nancy-low/high groupings, enabling full five-grade NHI prediction. On a multicenter dataset of H&E-stained colon biopsies from three hospitals (2019-2025), we evaluate multiple foundation model encoders and aggregation strategies. We find that foundation model choice and resolution substantially affect performance, with Virchow2 providing the most consistent gains, and that a simple ensembling rule improves five-grade NHI prediction compared to a hierarchical gating baseline. Overall, our results demonstrate that weakly supervised MIL with modern foundation-model representations can provide robust, interpretable UC histology activity assessment in realistic multicenter settings.