Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.13831 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910022327336960 |
|---|---|
| author | Bu, Zhenyu Xie, Yuanxin Zhou, Guang-Quan |
| author_facet | Bu, Zhenyu Xie, Yuanxin Zhou, Guang-Quan |
| contents | Ultrasound denoising is essential for mitigating speckle-induced degradations, thereby enhancing image quality and improving diagnostic reliability. Nevertheless, because speckle patterns inherently encode both texture and fine anatomical details, effectively suppressing noise while preserving structural fidelity remains a significant challenge. In this study, we propose a prior-guided hierarchical instance-pixel contrastive learning model for ultrasound denoising, designed to promote noise-invariant and structure-aware feature representations by maximizing the separability between noisy and clean samples at both pixel and instance levels. Specifically, a statistics-guided pixel-level contrastive learning strategy is introduced to enhance distributional discrepancies between noisy and clean pixels, thereby improving local structural consistency. Concurrently, a memory bank is employed to facilitate instance-level contrastive learning in the feature space, encouraging representations that more faithfully approximate the underlying data distribution. Furthermore, a hybrid Transformer-CNN architecture is adopted, coupling a Transformer-based encoder for global context modeling with a CNN-based decoder optimized for fine-grained anatomical structure restoration, thus enabling complementary exploitation of long-range dependencies and local texture details. Extensive evaluations on two publicly available ultrasound datasets demonstrate that the proposed model consistently outperforms existing methods, confirming its effectiveness and superiority. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13831 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Prior-guided Hierarchical Instance-pixel Contrastive Learning for Ultrasound Speckle Noise Suppression Bu, Zhenyu Xie, Yuanxin Zhou, Guang-Quan Computer Vision and Pattern Recognition Ultrasound denoising is essential for mitigating speckle-induced degradations, thereby enhancing image quality and improving diagnostic reliability. Nevertheless, because speckle patterns inherently encode both texture and fine anatomical details, effectively suppressing noise while preserving structural fidelity remains a significant challenge. In this study, we propose a prior-guided hierarchical instance-pixel contrastive learning model for ultrasound denoising, designed to promote noise-invariant and structure-aware feature representations by maximizing the separability between noisy and clean samples at both pixel and instance levels. Specifically, a statistics-guided pixel-level contrastive learning strategy is introduced to enhance distributional discrepancies between noisy and clean pixels, thereby improving local structural consistency. Concurrently, a memory bank is employed to facilitate instance-level contrastive learning in the feature space, encouraging representations that more faithfully approximate the underlying data distribution. Furthermore, a hybrid Transformer-CNN architecture is adopted, coupling a Transformer-based encoder for global context modeling with a CNN-based decoder optimized for fine-grained anatomical structure restoration, thus enabling complementary exploitation of long-range dependencies and local texture details. Extensive evaluations on two publicly available ultrasound datasets demonstrate that the proposed model consistently outperforms existing methods, confirming its effectiveness and superiority. |
| title | Prior-guided Hierarchical Instance-pixel Contrastive Learning for Ultrasound Speckle Noise Suppression |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.13831 |