MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classification
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_ | 1866912443004878848 |
|---|---|
| author | Drexlin, David Jacob Dippel, Jonas Hense, Julius Prenißl, Niklas Montavon, Grégoire Klauschen, Frederick Müller, Klaus-Robert |
| author_facet | Drexlin, David Jacob Dippel, Jonas Hense, Julius Prenißl, Niklas Montavon, Grégoire Klauschen, Frederick Müller, Klaus-Robert |
| contents | Deep learning models have made significant advances in histological prediction tasks in recent years. However, for adaptation in clinical practice, their lack of robustness to varying conditions such as staining, scanner, hospital, and demographics is still a limiting factor: if trained on overrepresented subpopulations, models regularly struggle with less frequent patterns, leading to shortcut learning and biased predictions. Large-scale foundation models have not fully eliminated this issue. Therefore, we propose a novel approach explicitly modeling such metadata into a Metadata-guided generative Diffusion model framework (MeDi). MeDi allows for a targeted augmentation of underrepresented subpopulations with synthetic data, which balances limited training data and mitigates biases in downstream models. We experimentally show that MeDi generates high-quality histopathology images for unseen subpopulations in TCGA, boosts the overall fidelity of the generated images, and enables improvements in performance for downstream classifiers on datasets with subpopulation shifts. Our work is a proof-of-concept towards better mitigating data biases with generative models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17140 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classification Drexlin, David Jacob Dippel, Jonas Hense, Julius Prenißl, Niklas Montavon, Grégoire Klauschen, Frederick Müller, Klaus-Robert Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Deep learning models have made significant advances in histological prediction tasks in recent years. However, for adaptation in clinical practice, their lack of robustness to varying conditions such as staining, scanner, hospital, and demographics is still a limiting factor: if trained on overrepresented subpopulations, models regularly struggle with less frequent patterns, leading to shortcut learning and biased predictions. Large-scale foundation models have not fully eliminated this issue. Therefore, we propose a novel approach explicitly modeling such metadata into a Metadata-guided generative Diffusion model framework (MeDi). MeDi allows for a targeted augmentation of underrepresented subpopulations with synthetic data, which balances limited training data and mitigates biases in downstream models. We experimentally show that MeDi generates high-quality histopathology images for unseen subpopulations in TCGA, boosts the overall fidelity of the generated images, and enables improvements in performance for downstream classifiers on datasets with subpopulation shifts. Our work is a proof-of-concept towards better mitigating data biases with generative models. |
| title | MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classification |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.17140 |