Streamline pathology foundation model by cross-magnification distillation
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_ | 1866912962097184768 |
|---|---|
| author | Su, Ziyu Akbar, Abdul Rehman Sajjad, Usama Parwani, Anil V. Niazi, Muhammad Khalid Khan |
| author_facet | Su, Ziyu Akbar, Abdul Rehman Sajjad, Usama Parwani, Anil V. Niazi, Muhammad Khalid Khan |
| contents | Foundation models (FM) have transformed computational pathology but remain computationally prohibitive for clinical deployment due to their massive parameter counts and high-magnification processing requirements. Here, we introduce XMAG, a lightweight FM developed through corss-magnification distillation that transfers knowledge from state-of-the-art 20x magnification teacher to an efficient 5x magnification student architecture. XMAG employs a compact backbone and operates entirely at 5x, requiring 11.3 times fewer patches per whole slide image (WSI) compared to existing approaches. Our Novel distillation framework incorporates dual-level knowledge transfer, aligning both global image representations and local spatial token mapping. We trained XMAG on 3.49 million images curated from publicly available datasets and evaluated performance across six clinically relevant histopathology analysis tasks spanning multiple cancer types. XMAG achieved diagnostic accuracy within 1% of substantially larger foundation models while delivering 30-fold processing acceleration, reaching 8.8 WSIs per minute processing speed. Our cross-institutional validation confirmed robust generalization. Further, we developed an end-to-end training strategy to further boost our model's performance to approach the larger FMs' performance. These results establish cross-magnification distillation as a viable approach for deploying FM capabilities in resource-constrained clinical environments, potentially enabling real-time pathology AI integration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23097 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Streamline pathology foundation model by cross-magnification distillation Su, Ziyu Akbar, Abdul Rehman Sajjad, Usama Parwani, Anil V. Niazi, Muhammad Khalid Khan Computer Vision and Pattern Recognition Foundation models (FM) have transformed computational pathology but remain computationally prohibitive for clinical deployment due to their massive parameter counts and high-magnification processing requirements. Here, we introduce XMAG, a lightweight FM developed through corss-magnification distillation that transfers knowledge from state-of-the-art 20x magnification teacher to an efficient 5x magnification student architecture. XMAG employs a compact backbone and operates entirely at 5x, requiring 11.3 times fewer patches per whole slide image (WSI) compared to existing approaches. Our Novel distillation framework incorporates dual-level knowledge transfer, aligning both global image representations and local spatial token mapping. We trained XMAG on 3.49 million images curated from publicly available datasets and evaluated performance across six clinically relevant histopathology analysis tasks spanning multiple cancer types. XMAG achieved diagnostic accuracy within 1% of substantially larger foundation models while delivering 30-fold processing acceleration, reaching 8.8 WSIs per minute processing speed. Our cross-institutional validation confirmed robust generalization. Further, we developed an end-to-end training strategy to further boost our model's performance to approach the larger FMs' performance. These results establish cross-magnification distillation as a viable approach for deploying FM capabilities in resource-constrained clinical environments, potentially enabling real-time pathology AI integration. |
| title | Streamline pathology foundation model by cross-magnification distillation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.23097 |