Benjamin Adjadj, Pierre-Antoine Bannier, Guillaume Horent, Sebastien Mandela, Gary Klajer, Aurore Lyon, Kathryn Schutte, Ulysse Marteau, Valentin Gaury, Laura Dumont, Thomas Mathieu, Reda Belbahri, Benoît Schmauch, Eric Durand, Katharina Von Loga, Lucie Gillet
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 5× fewer parameters. In addition, we show that HistoPLUS robustly transfers to two oncology indications unseen during training and allows interpretable biomarker discovery in downstream tasks, outperforming clinical baselines and prior deep learning methods. To support broader TME biomarker research, we release the model weights and inference code.