Molecular-driven Foundation Model for Oncologic Pathology
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929689314983936 |
|---|---|
| author | Vaidya, Anurag Zhang, Andrew Jaume, Guillaume Song, Andrew H. Ding, Tong Wagner, Sophia J. Lu, Ming Y. Doucet, Paul Robertson, Harry Almagro-Perez, Cristina Chen, Richard J. ElHarouni, Dina Ayoub, Georges Bossi, Connor Ligon, Keith L. Gerber, Georg Le, Long Phi Mahmood, Faisal |
| author_facet | Vaidya, Anurag Zhang, Andrew Jaume, Guillaume Song, Andrew H. Ding, Tong Wagner, Sophia J. Lu, Ming Y. Doucet, Paul Robertson, Harry Almagro-Perez, Cristina Chen, Richard J. ElHarouni, Dina Ayoub, Georges Bossi, Connor Ligon, Keith L. Gerber, Georg Le, Long Phi Mahmood, Faisal |
| contents | Foundation models are reshaping computational pathology by enabling transfer learning, where models pre-trained on vast datasets can be adapted for downstream diagnostic, prognostic, and therapeutic response tasks. Despite these advances, foundation models are still limited in their ability to encode the entire gigapixel whole-slide images without additional training and often lack complementary multimodal data. Here, we introduce Threads, a slide-level foundation model capable of generating universal representations of whole-slide images of any size. Threads was pre-trained using a multimodal learning approach on a diverse cohort of 47,171 hematoxylin and eosin (H&E)-stained tissue sections, paired with corresponding genomic and transcriptomic profiles - the largest such paired dataset to be used for foundation model development to date. This unique training paradigm enables Threads to capture the tissue's underlying molecular composition, yielding powerful representations applicable to a wide array of downstream tasks. In extensive benchmarking across 54 oncology tasks, including clinical subtyping, grading, mutation prediction, immunohistochemistry status determination, treatment response prediction, and survival prediction, Threads outperformed all baselines while demonstrating remarkable generalizability and label efficiency. It is particularly well suited for predicting rare events, further emphasizing its clinical utility. We intend to make the model publicly available for the broader community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16652 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Molecular-driven Foundation Model for Oncologic Pathology Vaidya, Anurag Zhang, Andrew Jaume, Guillaume Song, Andrew H. Ding, Tong Wagner, Sophia J. Lu, Ming Y. Doucet, Paul Robertson, Harry Almagro-Perez, Cristina Chen, Richard J. ElHarouni, Dina Ayoub, Georges Bossi, Connor Ligon, Keith L. Gerber, Georg Le, Long Phi Mahmood, Faisal Computer Vision and Pattern Recognition Artificial Intelligence Foundation models are reshaping computational pathology by enabling transfer learning, where models pre-trained on vast datasets can be adapted for downstream diagnostic, prognostic, and therapeutic response tasks. Despite these advances, foundation models are still limited in their ability to encode the entire gigapixel whole-slide images without additional training and often lack complementary multimodal data. Here, we introduce Threads, a slide-level foundation model capable of generating universal representations of whole-slide images of any size. Threads was pre-trained using a multimodal learning approach on a diverse cohort of 47,171 hematoxylin and eosin (H&E)-stained tissue sections, paired with corresponding genomic and transcriptomic profiles - the largest such paired dataset to be used for foundation model development to date. This unique training paradigm enables Threads to capture the tissue's underlying molecular composition, yielding powerful representations applicable to a wide array of downstream tasks. In extensive benchmarking across 54 oncology tasks, including clinical subtyping, grading, mutation prediction, immunohistochemistry status determination, treatment response prediction, and survival prediction, Threads outperformed all baselines while demonstrating remarkable generalizability and label efficiency. It is particularly well suited for predicting rare events, further emphasizing its clinical utility. We intend to make the model publicly available for the broader community. |
| title | Molecular-driven Foundation Model for Oncologic Pathology |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2501.16652 |