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/.
@article{arxiv.2508.09926,
title = {Towards Comprehensive Cellular Characterisation of H&E slides},
author = {Benjamin Adjadj and Pierre-Antoine Bannier and Guillaume Horent and Sebastien Mandela and Aurore Lyon and Kathryn Schutte and Ulysse Marteau and Valentin Gaury and Laura Dumont and Thomas Mathieu and MOSAIC consortium and Reda Belbahri and Benoît Schmauch and Eric Durand and Katharina Von Loga and Lucie Gillet},
journal= {arXiv preprint arXiv:2508.09926},
year = {2025}
}