解决医学影像中的虚假关联，提升模型泛化能力。
MIMM-X: Disentangling Spurious Correlations for Medical Image Analysis
- 通过最小化多类虚假关联的互信息，解耦因果特征。
- 在三个数据集上显著降低虚假关联导致的误判率。
- 适合关注医学影像模型可解释性与鲁棒性的研究者。
深度学习模型在医学任务中表现优异，但常因虚假相关性（即捷径学习）导致在新环境下的泛化能力差。尤其在医学影像中，多种虚假相关性可能共存，误分类后果严重。我们提出MIMM-X框架，通过最小化多个虚假相关性的互信息，解耦因果特征，使预测基于真实的因果关系而非数据集特定的捷径。我们在三个数据集（UK Biobank、NAKO、CheXpert）和两种成像模态（MRI与X射线）上评估MIMM-X，结果表明其能有效缓解多重虚假相关性的捷径学习问题。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。