MIMM-X: Disentangling Spurious Correlations for Medical Image Analysis
This addresses the critical issue of unreliable deep learning models in medical imaging, where spurious correlations can lead to dangerous misdiagnoses, representing a domain-specific advancement.
The paper tackles the problem of spurious correlations (shortcut learning) in medical image analysis, which can cause poor generalization and severe misclassifications, by proposing MIMM-X, a framework that disentangles causal features from multiple spurious correlations through mutual information minimization, and results show it effectively mitigates shortcut learning across three datasets and two imaging modalities.
Deep learning models can excel on medical tasks, yet often experience spurious correlations, known as shortcut learning, leading to poor generalization in new environments. Particularly in medical imaging, where multiple spurious correlations can coexist, misclassifications can have severe consequences. We propose MIMM-X, a framework that disentangles causal features from multiple spurious correlations by minimizing their mutual information. It enables predictions based on true underlying causal relationships rather than dataset-specific shortcuts. We evaluate MIMM-X on three datasets (UK Biobank, NAKO, CheXpert) across two imaging modalities (MRI and X-ray). Results demonstrate that MIMM-X effectively mitigates shortcut learning of multiple spurious correlations.