Towards Comprehensive Cellular Characterisation of H&E slides

TL;DR

HistoPLUS is a new model that significantly improves cell detection, segmentation, and classification on H&E slides, especially for understudied cell types, with better accuracy, fewer parameters, and strong cross-domain transferability.

Contribution

The paper introduces HistoPLUS, a novel model trained on a large pan-cancer dataset, achieving state-of-the-art performance and enabling study of previously understudied cell types.

Findings

Outperforms existing models in detection quality by 5.2%.

Improves F1 classification score by 23.7%.

Enables analysis of 7 understudied cell types.

Abstract

Cell detection, segmentation and classification are essential for analyzing tumor microenvironments (TME) on hematoxylin and eosin (H&E) slides. Existing methods suffer from poor performance on understudied cell types (rare or not present in public datasets) and limited cross-domain generalization. To address these shortcomings, we introduce HistoPLUS, a state-of-the-art model for cell analysis, trained on a novel curated pan-cancer dataset of 108,722 nuclei covering 13 cell types. In external validation across 4 independent cohorts, HistoPLUS outperforms current state-of-the-art models in detection quality by 5.2% and overall F1 classification score by 23.7%, while using 5x fewer parameters. Notably, HistoPLUS unlocks the study of 7 understudied cell types and brings significant improvements on 8 of 13 cell types. Moreover, we show that HistoPLUS robustly transfers to two oncology indications unseen during training. To support broader TME biomarker research, we release the model weights and inference code at https://github.com/owkin/histoplus/.