Source Matters: Source Dataset Impact on Model Robustness in Medical Imaging
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_ | 1866917752372985856 |
|---|---|
| author | Juodelyte, Dovile Lu, Yucheng Jiménez-Sánchez, Amelia Bottazzi, Sabrina Ferrante, Enzo Cheplygina, Veronika |
| author_facet | Juodelyte, Dovile Lu, Yucheng Jiménez-Sánchez, Amelia Bottazzi, Sabrina Ferrante, Enzo Cheplygina, Veronika |
| contents | Transfer learning has become an essential part of medical imaging classification algorithms, often leveraging ImageNet weights. The domain shift from natural to medical images has prompted alternatives such as RadImageNet, often showing comparable classification performance. However, it remains unclear whether the performance gains from transfer learning stem from improved generalization or shortcut learning. To address this, we conceptualize confounders by introducing the Medical Imaging Contextualized Confounder Taxonomy (MICCAT) and investigate a range of confounders across it -- whether synthetic or sampled from the data -- using two public chest X-ray and CT datasets. We show that ImageNet and RadImageNet achieve comparable classification performance, yet ImageNet is much more prone to overfitting to confounders. We recommend that researchers using ImageNet-pretrained models reexamine their model robustness by conducting similar experiments. Our code and experiments are available at https://github.com/DovileDo/source-matters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04484 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Source Matters: Source Dataset Impact on Model Robustness in Medical Imaging Juodelyte, Dovile Lu, Yucheng Jiménez-Sánchez, Amelia Bottazzi, Sabrina Ferrante, Enzo Cheplygina, Veronika Computer Vision and Pattern Recognition Machine Learning Transfer learning has become an essential part of medical imaging classification algorithms, often leveraging ImageNet weights. The domain shift from natural to medical images has prompted alternatives such as RadImageNet, often showing comparable classification performance. However, it remains unclear whether the performance gains from transfer learning stem from improved generalization or shortcut learning. To address this, we conceptualize confounders by introducing the Medical Imaging Contextualized Confounder Taxonomy (MICCAT) and investigate a range of confounders across it -- whether synthetic or sampled from the data -- using two public chest X-ray and CT datasets. We show that ImageNet and RadImageNet achieve comparable classification performance, yet ImageNet is much more prone to overfitting to confounders. We recommend that researchers using ImageNet-pretrained models reexamine their model robustness by conducting similar experiments. Our code and experiments are available at https://github.com/DovileDo/source-matters. |
| title | Source Matters: Source Dataset Impact on Model Robustness in Medical Imaging |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.04484 |