Safety
Understanding Sources of Demographic Predictability in Brain MRI via Disentangling Anatomy and Contrast
arXiv:2603.04113v2 Announce Type: replace-cross Abstract: Demographic attributes can be predicted from medical images, raising concerns about bias in clinical AI systems. In X-ray imaging, acquisition
arXiv:2603.04113v2 Announce Type: replace-cross Abstract: Demographic attributes can be predicted from medical images, raising concerns about bias in clinical AI systems. In X-ray imaging, acquisition characteristics have been shown to contribute substantially to this predictability. Whether the same holds in brain MRI remains unclear, as anatomical variation and acquisition-dependent contrast are deeply entangled in the image formation process, obscuring the origins of demographic signal. To address this, we propose a controlled framework based on disentangled representation learning, decomposing brain MRI into anatomy-focused representations that suppress acquisition influence and contrast embeddings that capture acquisition-dependent characteristics. Training predictive models for age, sex, and race on full images, anatomical representations, and contrast embeddings allows us to quantify the relative contributions of structure and acquisition to the demographic signal. Across three datasets and multiple MRI sequences, demographic predictability is found to be driven primarily by anatomical variation, with anatomy-focused representations largely preserving the performance of models trained on raw images. Contrast embeddings retain a weaker signal that is dataset-specific and does not generalise across sites. These findings suggest that effective mitigation must explicitly account for the primarily anatomical and secondarily acquisition-dependent origins of demographic signal, ensuring that any bias reduction generalizes robustly across domains.
Related
- BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding
- MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation
- Assessing Trustworthiness of AI Training Dataset using Subjective Logic -- A Use Case on Bias
- CURE: Curriculum-guided Multi-task Training for Reliable Anatomy Grounded Report Generation
Source: arXiv cs.AI | 2026-07-15