Science and Technology Production
Proceedings of the MICCAI Workshop on Applications of Medical AI (AMAI) 2024 - Source Matters: Source Dataset Impact on Model Robustness in Medical Imaging
Congress
Authorship:
Dovile Juodelyte ; Yucheng Lu ; Amelia Jimenez-Sanchez ; Sabrina Bottazzi ; FERRANTE, ENZO ; Veronika CheplyginaDate:
2024Publishing House and Editing Place:
SpringerSummary *
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 . Information provided by the agent in SIGEVAKey Words
pretrainingimage classificationsource datasetstransfer learning