Source Matters: Source Dataset Impact on Model Robustness in Medical Imaging
This work addresses robustness issues in medical imaging models, highlighting risks of shortcut learning, but it is incremental as it builds on existing transfer learning methods.
The study investigated how the source dataset used for transfer learning affects model robustness in medical imaging, finding that while ImageNet and RadImageNet achieve comparable classification performance, ImageNet is significantly more prone to overfitting to confounders.
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.