Key result
H-CSCA module improves LAA segmentation accuracy over baseline to a ~0.96 Dice coefficient.
Why the study?
Accurate LAA delineation is vital for LAAO planning and device sizing, but TTE segmentation is challenged by speckle noise, acoustic shadowing, low or variable contrast, anatomical variability, and limited annotated data.
Does the H-CSCA module improve left atrial appendage segmentation accuracy in echocardiography compared to the MSCCA-UNet baseline?
Does the H-CSCA module improve left atrial appendage segmentation accuracy in echocardiography compared to the MSCCA-UNet baseline?
The H-CSCA module improves the accuracy and stability of left atrial appendage segmentation in echocardiography, potentially aiding LAA occlusion planning.
May aid LAA occlusion planning via refined echocardiography segmentation; leaves open prospective clinical validation.
Accurate left atrial appendage (LAA) delineation is vital for atrial fibrillation-related left atrial appendage occlusion (LAAO) planning and device sizing; yet transthoracic echocardiography (TTE) segmentation is challenged by speckle noise, acoustic shadowing, low or variable contrast, pronounced anatomical variability, and limited annotated data. We propose a lightweight, plug-in module, the Hierarchical Cross-Scale Consistency with Gated Routing (H-CSCA), which preserves the U-Net topology and can be integrated into existing U-Net decoders as a drop-in replacement for skip connections with minimal architectural changes and parameter overhead. Our key contribution is to couple cross-scale cycle consistency with learnable gated routing within the U-Net decoder, enabling controllable fusion for echo boundary refinement. Our model aligns the encoder and decoder features across neighboring scales and selectively routes information between them to reinforce fine boundary cues without relying on transformer-heavy backbones. Unlike prior multi-scale U-Net variants that rely on fixed skip and fusion pathways, H-CSCA explicitly enforces cross-scale agreement and adaptively selects which scales contribute to refinement via learnable routing. We evaluated our method on an anonymized dataset of LAA TTE views annotated by cardiologists, with a strict patient-level split (16 training, 5 validation, 5 test; held-out, locked test set). Compared to the MSCCA-UNet baseline, H-CSCA improved the Dice coefficient from 0.9490 ± 0.0030 to 0.9598 ± 0.0026 and IoU from 0.9040 ± 0.0040 to 0.9232 ± 0.0037, with only a marginal parameter increase (15.45M to 15.71M). Boundary quality also improved, reducing mean absolute distance from 0.8223 ± 0.0791 to 0.7918 ± 0.0613 and reducing worst-case boundary deviation (Hausdorff) by approximately 2%. Overall, H-CSCA yields sharper, more stable contours at minimal computational cost, supporting reliable LAAO planning and guidance in data-limited echocardiography workflows.
No takes yet. Share an insight, caveat, or question.
Zadeh et al. (2026) studied Left atrial appendage segmentation (n=26). Hierarchical Cross-Scale Consistency with Gated Routing (H-CSCA) vs. MSCCA-UNet baseline was evaluated on Dice coefficient. The H-CSCA module improved the Dice coefficient for left atrial appendage segmentation to 0.9598 compared to 0.9490 for the MSCCA-UNet baseline.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: