Curia: A Multi-Modal Foundation Model for Radiology
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914027734564864 |
|---|---|
| author | Dancette, Corentin Khlaut, Julien Saporta, Antoine Philippe, Helene Ferreres, Elodie Callard, Baptiste Danielou, Théo Alberge, Léo Machado, Léo Tordjman, Daniel Dupuis, Julie Floch, Korentin Le Terrail, Jean Du Moshiri, Mariam Dercle, Laurent Boeken, Tom Gregory, Jules Ronot, Maxime Legou, François Roux, Pascal Sapoval, Marc Manceron, Pierre Hérent, Paul |
| author_facet | Dancette, Corentin Khlaut, Julien Saporta, Antoine Philippe, Helene Ferreres, Elodie Callard, Baptiste Danielou, Théo Alberge, Léo Machado, Léo Tordjman, Daniel Dupuis, Julie Floch, Korentin Le Terrail, Jean Du Moshiri, Mariam Dercle, Laurent Boeken, Tom Gregory, Jules Ronot, Maxime Legou, François Roux, Pascal Sapoval, Marc Manceron, Pierre Hérent, Paul |
| contents | AI-assisted radiological interpretation is based on predominantly narrow, single-task models. This approach is impractical for covering the vast spectrum of imaging modalities, diseases, and radiological findings. Foundation models (FMs) hold the promise of broad generalization across modalities and in low-data settings. However, this potential has remained largely unrealized in radiology. We introduce Curia, a foundation model trained on the entire cross-sectional imaging output of a major hospital over several years, which to our knowledge is the largest such corpus of real-world data-encompassing 150,000 exams (130 TB). On a newly curated 19-task external validation benchmark, Curia accurately identifies organs, detects conditions like brain hemorrhages and myocardial infarctions, and predicts outcomes in tumor staging. Curia meets or surpasses the performance of radiologists and recent foundation models, and exhibits clinically significant emergent properties in cross-modality, and low-data regimes. To accelerate progress, we release our base model's weights at https://huggingface.co/raidium/curia. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06830 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Curia: A Multi-Modal Foundation Model for Radiology Dancette, Corentin Khlaut, Julien Saporta, Antoine Philippe, Helene Ferreres, Elodie Callard, Baptiste Danielou, Théo Alberge, Léo Machado, Léo Tordjman, Daniel Dupuis, Julie Floch, Korentin Le Terrail, Jean Du Moshiri, Mariam Dercle, Laurent Boeken, Tom Gregory, Jules Ronot, Maxime Legou, François Roux, Pascal Sapoval, Marc Manceron, Pierre Hérent, Paul Computer Vision and Pattern Recognition Machine Learning AI-assisted radiological interpretation is based on predominantly narrow, single-task models. This approach is impractical for covering the vast spectrum of imaging modalities, diseases, and radiological findings. Foundation models (FMs) hold the promise of broad generalization across modalities and in low-data settings. However, this potential has remained largely unrealized in radiology. We introduce Curia, a foundation model trained on the entire cross-sectional imaging output of a major hospital over several years, which to our knowledge is the largest such corpus of real-world data-encompassing 150,000 exams (130 TB). On a newly curated 19-task external validation benchmark, Curia accurately identifies organs, detects conditions like brain hemorrhages and myocardial infarctions, and predicts outcomes in tumor staging. Curia meets or surpasses the performance of radiologists and recent foundation models, and exhibits clinically significant emergent properties in cross-modality, and low-data regimes. To accelerate progress, we release our base model's weights at https://huggingface.co/raidium/curia. |
| title | Curia: A Multi-Modal Foundation Model for Radiology |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2509.06830 |