Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.13027 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911463416791040 |
|---|---|
| author | Neidlinger, Peter Lenz, Tim Foersch, Sebastian Loeffler, Chiara M. L. Clusmann, Jan Gustav, Marco Shaktah, Lawrence A. Langer, Rupert Dislich, Bastian Boardman, Lisa A. French, Amy J. Goode, Ellen L. Gsur, Andrea Brezina, Stefanie Gunter, Marc J. Steinfelder, Robert Behrens, Hans-Michael Röcken, Christoph Harrison, Tabitha Peters, Ulrike Phipps, Amanda I. Curigliano, Giuseppe Fusco, Nicola Marra, Antonio Hoffmeister, Michael Brenner, Hermann Kather, Jakob Nikolas |
| author_facet | Neidlinger, Peter Lenz, Tim Foersch, Sebastian Loeffler, Chiara M. L. Clusmann, Jan Gustav, Marco Shaktah, Lawrence A. Langer, Rupert Dislich, Bastian Boardman, Lisa A. French, Amy J. Goode, Ellen L. Gsur, Andrea Brezina, Stefanie Gunter, Marc J. Steinfelder, Robert Behrens, Hans-Michael Röcken, Christoph Harrison, Tabitha Peters, Ulrike Phipps, Amanda I. Curigliano, Giuseppe Fusco, Nicola Marra, Antonio Hoffmeister, Michael Brenner, Hermann Kather, Jakob Nikolas |
| contents | Artificial intelligence (AI) has transformed digital pathology by enabling biomarker prediction from high-resolution whole-slide images (WSIs). However, current methods are computationally inefficient, processing thousands of redundant tiles per WSI and requiring complex aggregator models. We introduce EAGLE (Efficient Approach for Guided Local Examination), a deep learning framework that emulates pathologists by selectively analyzing informative regions. EAGLE incorporates two foundation models: CHIEF for efficient tile selection and Virchow2 for extracting high-quality features. Benchmarking was conducted against leading slide- and tile-level foundation models across 43 tasks from nine cancer types, spanning morphology, biomarker prediction, treatment response and prognosis. EAGLE outperformed state-of-the-art patch aggregation methods by up to 23% and achieved the highest AUROC overall. It processed a slide in 2.27 seconds, reducing computational time by more than 99% compared to existing models. This efficiency enables real-time workflows, allows rapid review of the exact tiles used for each prediction, and reduces dependence on high-performance computing, making AI-powered pathology more accessible. By reliably identifying meaningful regions and minimizing artifacts, EAGLE provides robust and auditable outputs, supported by systematic negative controls and attention concentration analyses. Its unified embedding enables rapid slide searches, integration into multi-omics pipelines and emerging clinical foundation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13027 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A deep learning framework for efficient pathology image analysis Neidlinger, Peter Lenz, Tim Foersch, Sebastian Loeffler, Chiara M. L. Clusmann, Jan Gustav, Marco Shaktah, Lawrence A. Langer, Rupert Dislich, Bastian Boardman, Lisa A. French, Amy J. Goode, Ellen L. Gsur, Andrea Brezina, Stefanie Gunter, Marc J. Steinfelder, Robert Behrens, Hans-Michael Röcken, Christoph Harrison, Tabitha Peters, Ulrike Phipps, Amanda I. Curigliano, Giuseppe Fusco, Nicola Marra, Antonio Hoffmeister, Michael Brenner, Hermann Kather, Jakob Nikolas Computer Vision and Pattern Recognition Artificial intelligence (AI) has transformed digital pathology by enabling biomarker prediction from high-resolution whole-slide images (WSIs). However, current methods are computationally inefficient, processing thousands of redundant tiles per WSI and requiring complex aggregator models. We introduce EAGLE (Efficient Approach for Guided Local Examination), a deep learning framework that emulates pathologists by selectively analyzing informative regions. EAGLE incorporates two foundation models: CHIEF for efficient tile selection and Virchow2 for extracting high-quality features. Benchmarking was conducted against leading slide- and tile-level foundation models across 43 tasks from nine cancer types, spanning morphology, biomarker prediction, treatment response and prognosis. EAGLE outperformed state-of-the-art patch aggregation methods by up to 23% and achieved the highest AUROC overall. It processed a slide in 2.27 seconds, reducing computational time by more than 99% compared to existing models. This efficiency enables real-time workflows, allows rapid review of the exact tiles used for each prediction, and reduces dependence on high-performance computing, making AI-powered pathology more accessible. By reliably identifying meaningful regions and minimizing artifacts, EAGLE provides robust and auditable outputs, supported by systematic negative controls and attention concentration analyses. Its unified embedding enables rapid slide searches, integration into multi-omics pipelines and emerging clinical foundation models. |
| title | A deep learning framework for efficient pathology image analysis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.13027 |