AI RESEARCH
Motion-Guided Causal Disentanglement for Robust Multi-View Cine Cardiac MRI Diagnosis
arXiv CS.CV
•
ArXi:2606.04414v1 Announce Type: new Multi-view cardiac magnetic resonance (CMR) imaging provides complementary anatomical information and is widely used for noninvasive disease assessment. Recent transformer-based models have nstrated strong representation learning capabilities for CMR analysis; however, they typically learn unified latent embeddings that entangle view-specific anatomical variations with disease-related features. Such entanglement biases classifiers toward structural attributes rather than view-invariant pathological patterns.