AI RESEARCH
Contour-Guided Query-Based Feature Fusion for Boundary-Aware and Generalizable Cardiac Ultrasound Segmentation
arXiv CS.CV
•
ArXi:2603.28110v1 Announce Type: new Accurate cardiac ultrasound segmentation is essential for reliable assessment of ventricular function in intelligent healthcare systems. However, echocardiographic images are challenging due to low contrast, speckle noise, irregular boundaries, and domain shifts across devices and patient populations. Existing methods, largely based on appearance-driven learning, often fail to preserve boundary precision and structural consistency under these conditions.