Contour-Guided Query-Based Feature Fusion for Boundary-Aware and Generalizable Cardiac Ultrasound Segmentation

TL;DR

This paper introduces CGQR-Net, a boundary-aware segmentation method for cardiac ultrasound images that leverages contour-guided queries and multi-resolution features to improve accuracy and robustness across datasets.

Contribution

The paper presents a novel contour-guided query refinement network that integrates structural priors with multi-scale features for improved boundary accuracy in ultrasound segmentation.

Findings

Enhanced boundary delineation and structural consistency.

Improved segmentation accuracy across datasets.

Robust performance under domain shifts and noise.

Abstract

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. To address these issues, we propose a Contour-Guided Query Refinement Network (CGQR-Net) for boundary-aware cardiac ultrasound segmentation. The framework integrates multi-resolution feature representations with contour-derived structural priors. An HRNet backbone preserves high-resolution spatial details while capturing multi-scale context. A coarse segmentation is first generated, from which anatomical contours are extracted and encoded into learnable query embeddings. These contour-guided queries interact with fused feature maps via cross-attention, enabling structure-aware refinement that improves boundary delineation and reduces noise artifacts. A dual-head supervision strategy jointly optimizes segmentation and boundary prediction to enforce structural consistency. The proposed method is evaluated on the CAMUS dataset and further validated on the CardiacNet dataset to assess cross-dataset generalization. Experimental results demonstrate improved segmentation accuracy, enhanced boundary precision, and robust performance across varying imaging conditions. These results highlight the effectiveness of integrating contour-level structural information with feature-level representations for reliable cardiac ultrasound segmentation.