mlsanityData to 7 Oct 2026

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

arXiv 2603.28110 ↗First posted 30 Mar 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 72 references that are in the map. First posted on arXiv 30 Mar 2026.

Builds on

36 of 72 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  7. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  8. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  9. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  10. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  11. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  12. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
24 more
  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  2. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  3. 2022Transformers in Medical Imaging: A Surveycited by 245
  4. 2019Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiographycited by 243
  5. 2018Boundary loss for highly unbalanced segmentationcited by 187
  6. 2021BEVT: BERT Pretraining of Video Transformerscited by 169
  7. 2018Unsupervised domain adaptation for medical imaging segmentation with self-ensemblingcited by 94
  8. 2020Cardiac Segmentation with Strong Anatomical Guaranteescited by 43
  9. 2024PEM: Prototype-based Efficient MaskFormer for Image Segmentationcited by 35
  10. 2022Multi-Task Learning with Multi-Query Transformer for Dense Predictioncited by 34
  11. 2019CANet: An Unsupervised Intrusion Detection System for High Dimensional CAN Bus Datacited by 28
  12. 2022Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionarycited by 22
  13. 2022Extending nnU-Net is all you needcited by 22
  14. 2022CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentationcited by 18
  15. 2016A Fully Convolutional Neural Network for Cardiac Segmentation in Short-Axis MRIcited by 16
  16. 2023Anatomically-aware Uncertainty for Semi-supervised Image Segmentationcited by 13
  17. 2024CardiacNet: Learning to Reconstruct Abnormalities for Cardiac Disease Assessment from Echocardiogram Videoscited by 11
  18. 2024CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extractioncited by 9
  19. 2025GATE3D: Generalized Attention-based Task-synergized Estimation in 3D*cited by 4
  20. 2023Query-guided Attention in Vision Transformers for Localizing Objects Using a Single Sketchcited by 3
  21. 2025DAM-Seg: Anatomically accurate cardiac segmentation using Dense Associative Networkscited by 3
  22. 2024MambaEviScrib: Mamba and Evidence-Guided Consistency Enhance CNN Robustness for Scribble-Based Weakly Supervised Ultrasound Image Segmentationcited by 1
  23. 2025Multitask Multimodal Self-Supervised Learning for Medical Imagescited by 1
  24. 2025VOST-SGG: VLM-Aided One-Stage Spatio-Temporal Scene Graph Generationcited by 1

Built on by

Not cited yet.