CardioSAM: Topology-Aware Decoder Design for High-Precision Cardiac MRI Segmentation
For clinicians requiring high-precision cardiac MRI segmentation, CardioSAM offers a method that outperforms existing baselines and matches expert-level accuracy, reducing manual segmentation burden.
CardioSAM introduces a hybrid architecture combining a frozen SAM encoder with a cardiac-specific decoder featuring topological priors and boundary refinement, achieving 93.39% Dice on the ACDC benchmark, surpassing nnU-Net by +3.89% and exceeding inter-expert agreement (91.2%).
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), demonstrate strong generalization but often lack the boundary precision required for clinical applications. To address this limitation, we propose CardioSAM, a hybrid architecture that combines the generalized feature extraction capability of a frozen SAM encoder with a lightweight, trainable cardiac-specific decoder. The proposed decoder introduces two key innovations: a Cardiac-Specific Attention module that incorporates anatomical topological priors, and a Boundary Refinement Module designed to improve tissue interface delineation. Experimental evaluation on the ACDC benchmark demonstrates that CardioSAM achieves a Dice coefficient of 93.39%, IoU of 87.61%, pixel accuracy of 99.20%, and HD95 of 4.2 mm. The proposed method surpasses strong baselines such as nnU-Net by +3.89% Dice and exceeds reported inter-expert agreement levels (91.2%), indicating its potential for reliable and clinically applicable cardiac segmentation.