Whole Slide Concepts: A Supervised Foundation Model For Pathological Images
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_ | 1866908787469713408 |
|---|---|
| author | Nicke, Till Schacherer, Daniela Schäfer, Jan Raphael Artysh, Natalia Prasse, Antje Homeyer, André Schenk, Andrea Höfener, Henning Lotz, Johannes |
| author_facet | Nicke, Till Schacherer, Daniela Schäfer, Jan Raphael Artysh, Natalia Prasse, Antje Homeyer, André Schenk, Andrea Höfener, Henning Lotz, Johannes |
| contents | Foundation models (FMs) are transforming computational pathology by offering new ways to analyze histopathology images. However, FMs typically require weeks of training on large databases, making their creation a resource-intensive process. In this paper, we present a training for foundation models from whole slide images using supervised, end-to-end, multitask learning on slide-level labels. Notably, it is the first model to incorporate cancer subtyping, risk estimation, and genetic mutation prediction into one model. The presented model outperforms self-supervised models on seven benchmark tasks while the training only required 5% of the computational resources. The results not only show that supervised training can outperform self-supervision with less data, but also offer a solution to annotation problems, as patient-based labels are widely available through routine clinical processes. Furthermore, an attention module provides a layer of explainability across different tasks and serves as a tumor detector for unseen cancer types. To address the issue of closed-source datasets, the model was fully trained on openly available data. The code and model weights are made available under https://github.com/FraunhoferMEVIS/MedicalMultitaskModeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05742 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Whole Slide Concepts: A Supervised Foundation Model For Pathological Images Nicke, Till Schacherer, Daniela Schäfer, Jan Raphael Artysh, Natalia Prasse, Antje Homeyer, André Schenk, Andrea Höfener, Henning Lotz, Johannes Image and Video Processing Computer Vision and Pattern Recognition Foundation models (FMs) are transforming computational pathology by offering new ways to analyze histopathology images. However, FMs typically require weeks of training on large databases, making their creation a resource-intensive process. In this paper, we present a training for foundation models from whole slide images using supervised, end-to-end, multitask learning on slide-level labels. Notably, it is the first model to incorporate cancer subtyping, risk estimation, and genetic mutation prediction into one model. The presented model outperforms self-supervised models on seven benchmark tasks while the training only required 5% of the computational resources. The results not only show that supervised training can outperform self-supervision with less data, but also offer a solution to annotation problems, as patient-based labels are widely available through routine clinical processes. Furthermore, an attention module provides a layer of explainability across different tasks and serves as a tumor detector for unseen cancer types. To address the issue of closed-source datasets, the model was fully trained on openly available data. The code and model weights are made available under https://github.com/FraunhoferMEVIS/MedicalMultitaskModeling. |
| title | Whole Slide Concepts: A Supervised Foundation Model For Pathological Images |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.05742 |