Anatomy-aware Spatio-Temporal Modeling for Echocardiography Segmentation

Echocardiography segmentation plays a central role in quantitative cardiovascular assessment. However, automated echocardiography segmentation remains challenging due to speckle noise, poorly defined anatomical boundaries, acquisition variability, and the limited anatomical coverage of existing benchmarks. Conventional segmentation methods demonstrate limited accuracy under such low image quality and domain shifts. Inspired by the observation that expert cardiologists can maintain reliable anatomical delineation by leveraging their structural understanding of the cardiac anatomy, we propose that incorporating anatomical priors into echocardiography segmentation models can improve both precision and robustness. To this end, we propose AST-Seg, an anatomy-aware spatio-temporal framework for echocardiography segmentation. AST-Seg introduces an anatomy-aware feature encoder that regularizes transformer attention with anatomy-derived spatial-relation priors, and a Deformable Spatio-Temporal Mamba module that captures localized and periodic cardiac motion through adaptive spatial aggregation followed by temporal state-space modeling. In addition, we curate an Echocardiography Anatomy (EA) dataset with pixel-level annotations for 12 clinically relevant cardiac anatomy, enabling comprehensive multi-structure cardiac interpretation. Extensive experiments on in-distribution CAMUS and EA datasets, as well as an out-of-distribution point-of-care echocardiography dataset, demonstrate that AST-Seg provides domain-generalized segmentation with improved precision.