Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.09926 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908514293645312 |
|---|---|
| author | Adjadj, Benjamin Bannier, Pierre-Antoine Horent, Guillaume Mandela, Sebastien Lyon, Aurore Schutte, Kathryn Marteau, Ulysse Gaury, Valentin Dumont, Laura Mathieu, Thomas consortium, MOSAIC Belbahri, Reda Schmauch, Benoît Durand, Eric Von Loga, Katharina Gillet, Lucie |
| author_facet | Adjadj, Benjamin Bannier, Pierre-Antoine Horent, Guillaume Mandela, Sebastien Lyon, Aurore Schutte, Kathryn Marteau, Ulysse Gaury, Valentin Dumont, Laura Mathieu, Thomas consortium, MOSAIC Belbahri, Reda Schmauch, Benoît Durand, Eric Von Loga, Katharina Gillet, Lucie |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09926 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Comprehensive Cellular Characterisation of H&E slides Adjadj, Benjamin Bannier, Pierre-Antoine Horent, Guillaume Mandela, Sebastien Lyon, Aurore Schutte, Kathryn Marteau, Ulysse Gaury, Valentin Dumont, Laura Mathieu, Thomas consortium, MOSAIC Belbahri, Reda Schmauch, Benoît Durand, Eric Von Loga, Katharina Gillet, Lucie Computer Vision and Pattern Recognition Quantitative Methods I.2.10; I.4.8 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/. |
| title | Towards Comprehensive Cellular Characterisation of H&E slides |
| topic | Computer Vision and Pattern Recognition Quantitative Methods I.2.10; I.4.8 |
| url | https://arxiv.org/abs/2508.09926 |