AI RESEARCH
CardioSAM: Topology-Aware Decoder Design for High-Precision Cardiac MRI Segmentation
arXiv CS.CV
•
ArXi:2604.03313v1 Announce Type: new Accurate segmentation of cardiac structures in cardiovascular magnetic resonance (CMR) images is essential for reliable diagnosis and treatment of cardiovascular diseases. However, manual segmentation remains time-consuming and suffers from significant inter-observer variability. Recent advances in deep learning, particularly foundation models such as the Segment Anything Model (SAM), nstrate strong generalization but often lack the boundary precision required for clinical applications.