Towards Large-Scale Training of Pathology Foundation Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929325698187264 |
|---|---|
| author | ai, kaiko. Aben, Nanne de Jong, Edwin D. Gatopoulos, Ioannis Känzig, Nicolas Karasikov, Mikhail Lagré, Axel Moser, Roman van Doorn, Joost Tang, Fei |
| author_facet | ai, kaiko. Aben, Nanne de Jong, Edwin D. Gatopoulos, Ioannis Känzig, Nicolas Karasikov, Mikhail Lagré, Axel Moser, Roman van Doorn, Joost Tang, Fei |
| contents | Driven by the recent advances in deep learning methods and, in particular, by the development of modern self-supervised learning algorithms, increased interest and efforts have been devoted to build foundation models (FMs) for medical images. In this work, we present our scalable training pipeline for large pathology imaging data, and a comprehensive analysis of various hyperparameter choices and training techniques for building pathology FMs. We release and make publicly available the first batch of our pathology FMs (https://github.com/kaiko-ai/towards_large_pathology_fms) trained on open-access TCGA whole slide images, a commonly used collection of pathology images. The experimental evaluation shows that our models reach state-of-the-art performance on various patch-level downstream tasks, ranging from breast cancer subtyping to colorectal nuclear segmentation. Finally, to unify the evaluation approaches used in the field and to simplify future comparisons of different FMs, we present an open-source framework (https://github.com/kaiko-ai/eva) designed for the consistent evaluation of pathology FMs across various downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15217 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Large-Scale Training of Pathology Foundation Models ai, kaiko. Aben, Nanne de Jong, Edwin D. Gatopoulos, Ioannis Känzig, Nicolas Karasikov, Mikhail Lagré, Axel Moser, Roman van Doorn, Joost Tang, Fei Computer Vision and Pattern Recognition Machine Learning Driven by the recent advances in deep learning methods and, in particular, by the development of modern self-supervised learning algorithms, increased interest and efforts have been devoted to build foundation models (FMs) for medical images. In this work, we present our scalable training pipeline for large pathology imaging data, and a comprehensive analysis of various hyperparameter choices and training techniques for building pathology FMs. We release and make publicly available the first batch of our pathology FMs (https://github.com/kaiko-ai/towards_large_pathology_fms) trained on open-access TCGA whole slide images, a commonly used collection of pathology images. The experimental evaluation shows that our models reach state-of-the-art performance on various patch-level downstream tasks, ranging from breast cancer subtyping to colorectal nuclear segmentation. Finally, to unify the evaluation approaches used in the field and to simplify future comparisons of different FMs, we present an open-source framework (https://github.com/kaiko-ai/eva) designed for the consistent evaluation of pathology FMs across various downstream tasks. |
| title | Towards Large-Scale Training of Pathology Foundation Models |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2404.15217 |