Noise-Aware Boundary-Enhanced Generative Learning for Ultrasound Speckle Reduction

• URL: http://arxiv.org/abs/2606.25009v2
• Date: Thu, 25 Jun 2026 13:13:11 GMT
• Title: Noise-Aware Boundary-Enhanced Generative Learning for Ultrasound Speckle Reduction
• Abstract summary: We propose a Noise-Aware Boundary-Enhanced Generative Learning (NBGL) framework for ultrasound speckle reduction.<n>NBGL simultaneously preserves annotated anatomical boundaries and adapts to varying noise levels.<n>It consistently outperforms state-of-the-art methods in speckle reduction and structural preservation across six noise levels.
• Score: 2.344716717625477
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ultrasound is a non-invasive, real-time, and cost-effective imaging technique widely used in clinical diagnosis. However, its diagnostic efficacy is often compromised by inherent speckle noise that degrades image quality and obscures underlying anatomical structures. Existing speckle reduction methods tend to over-smooth tissue boundaries and generalize poorly to heterogeneous noise levels. To address these limitations, we propose a Noise-Aware Boundary-Enhanced Generative Learning (NBGL) framework for ultrasound speckle reduction, which simultaneously preserves annotated anatomical boundaries and adapts to varying noise levels. The NBGL framework consists of a speckle reduction branch and a boundary enhancement branch. The former leverages generative learning to suppress speckle noise, while the latter learns boundary-sensitive representations to preserve target anatomical structures. Furthermore, a noise-aware interaction weight generation (NIWG) module estimates the speckle noise level via 3D Laplacian filtering and a median absolute deviation estimator, and translates it into an adaptive interaction weight. This weight is incorporated into a weighted feature-wise linear modulation (wFiLM) module to adaptively modulate cross-branch feature coupling, thereby improving robustness to varying noise levels. Extensive evaluations on 141 3D transvaginal ultrasound volumes demonstrate that NBGL consistently outperforms state-of-the-art methods in speckle reduction and structural preservation across six noise levels, while maintaining consistency with annotated anatomical boundaries.

Related papers

• A deep dictionary network-based foundation model for ultra-low-dose CT denoising [49.70293041079032]
  Ultra-low-dose computed tomography (ULDCT) reduces radiation exposure but suffers from severe noise that degrades diagnostic image quality.<n>Existing deep learning-based denoising methods are typically trained in an organ-specific fashion, resulting in limited generalization across heterogeneous multi?organ imaging scenarios.<n>We propose an architecture?able foundation model based on the deep dictionary network (DDN) for unified multi-organ ULDCT denoising.
  arXiv  Detail & Related papers  (2026-09-11T05:14:08Z)
• Null-Space Diffusion Restoration with Adaptive Uncertainty-Guided Fusion for Ultrasound Speckle Reduction [2.081691729410268]
  Ultrasound B-mode imaging commonly suffers from speckle noise and artifacts.<n>New uncertainty-guided null-space diffusion (UGNS) framework enforces consistency correction on a stabilized positive-envelope proxy.<n>It is successfully validated that UGNS effectively suppresses speckle noise while preserving fine spatial resolution.
  arXiv  Detail & Related papers  (2026-08-30T14:45:13Z)
• UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation [90.0896070825457]
  We propose a unified noise-driven framework that rethinks safety mechanisms through the lens of noise dynamics in diffusion processes.<n>Our key insight is that early-stage predicted noise exhibits inherent separability between normal and sexually explicit content.<n>We develop a lightweight noise-based detector achieving superior accuracy with virtually no computational overhead.
  arXiv  Detail & Related papers  (2026-07-18T14:03:39Z)
• Automatic Echocardiography Segmentation via Transition Probability Correlation for Stable Semantic Extraction [24.0739266805929]
  Improbable speckle noise and low signal-to-noise ratio lead to ambiguous semantic features and fragmented boundaries.<n>We design a STLSF module which comprises a window-matching-based semantic correction component and a semantics-guided texture enhancement component.<n>We achieve 93.87% Dice on CAMUS and 92.62% on EchoNet-Dynamic, with respective HD95 values of 3.29mm and 2.73mm.
  arXiv  Detail & Related papers  (2026-07-08T16:04:05Z)
• FSS-Net: Frequency-Spatial Synergy Network with Wavelet Attention for Carotid Artery Ultrasound Segmentation [11.152127159739736]
  We propose a Frequency-Spatial Synergy Network (FSS-Net) to achieve noise-robust and high-precision carotid artery segmentation.<n>The network integrates wavelet transform, multi-domain attention, and edge enhancement into a unified encoder-decoder architecture.<n>Experiments on carotid ultrasound datasets show that FSS-Net achieves a Dice score (DSC) of 96.46% and strong robustness under low SNR conditions.
  arXiv  Detail & Related papers  (2026-06-09T03:40:52Z)
• Decoupling Wavelet Sub-bands for Single Source Domain Generalization in Fundus Image Segmentation [2.8382282285875653]
  This research introduces WaveSDG, a new wavelet-guided segmentation network for domain generalization in fundus imaging.<n>It decouples anatomical structure from domain-specific appearance through a wavelet sub-band decomposition.<n>It consistently outperforms seven state-of-the-art datasets.
  arXiv  Detail & Related papers  (2026-03-30T14:04:45Z)
• FreqDINO: Frequency-Guided Adaptation for Generalized Boundary-Aware Ultrasound Image Segmentation [18.491659279102993]
  We propose FreqDINO, a frequency-guided segmentation framework that enhances boundary perception and structural consistency.<n>Specifically, we devise a Multi-scale Frequency Extraction and Alignment strategy to separate low-frequency structures and multi-scale high-frequency boundary details.<n>We also introduce a Frequency-Guided Boundary Refinement (FGBR) module that extracts boundary prototypes from high-frequency components and refines spatial features.
  arXiv  Detail & Related papers  (2025-12-12T07:15:38Z)
• MetaDCSeg: Robust Medical Image Segmentation via Meta Dynamic Center Weighting [77.31583168890633]
  Medical image segmentation is crucial for clinical applications, but it is frequently disrupted by noisy annotations and ambiguous anatomical boundaries.<n>We propose MetaDCSeg, a robust framework that learns optimal pixel-wise weights to suppress the influence of noisy ground-truth labels.<n>Our approach utilizes weighted feature distances for foreground, background, and boundary centers, directing the model's attention toward hard-to-segment pixels near ambiguous boundaries.
  arXiv  Detail & Related papers  (2025-11-24T08:51:02Z)
• Layer-wise Noise Guided Selective Wavelet Reconstruction for Robust Medical Image Segmentation [16.82406992858576]
  We proposeLayer-wise Noise-Guided Selective Wavelet Reconstruction (LNG-SWR)<n>During training, we inject small, zero-mean noise at multiple layers to learn a frequency-bias prior to steer representations away from noise-sensitive directions.<n>We then apply prior-guided selective wavelet reconstruction on the input/feature branch to achieve frequency adaptation.
  arXiv  Detail & Related papers  (2025-11-20T09:03:32Z)
• Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance [54.88271057438763]
  Noise Awareness Guidance (NAG) is a correction method that explicitly steers sampling trajectories to remain consistent with the pre-defined noise schedule.<n>NAG consistently mitigates noise shift and substantially improves the generation quality of mainstream diffusion models.
  arXiv  Detail & Related papers  (2025-10-14T13:31:34Z)
• GARD: Gamma-based Anatomical Restoration and Denoising for Retinal OCT [5.763765207893223]
  GARD (Gamma-based Anatomical Restoration and Denoising) is a novel deep learning approach for OCT image despeckling.<n>GARD employs a Denoising Diffusion Gamma Model to more accurately reflect the statistical properties of speckle.<n>We show GARD significantly outperforms traditional denoising methods and state-of-the-art deep learning models in terms of PSNR, SSIM, and MSE.
  arXiv  Detail & Related papers  (2025-09-12T15:24:41Z)
• Structure-Accurate Medical Image Translation via Dynamic Frequency Balance and Knowledge Guidance [60.33892654669606]
  Diffusion model is a powerful strategy to synthesize the required medical images.<n>Existing approaches still suffer from the problem of anatomical structure distortion due to the overfitting of high-frequency information.<n>We propose a novel method based on dynamic frequency balance and knowledge guidance.
  arXiv  Detail & Related papers  (2025-04-13T05:48:13Z)
• Epicardium Prompt-guided Real-time Cardiac Ultrasound Frame-to-volume Registration [50.602074919305636]
  This paper introduces a lightweight end-to-end Cardiac Ultrasound frame-to-volume Registration network, termed CU-Reg.<n>We use epicardium prompt-guided anatomical clues to reinforce the interaction of 2D sparse and 3D dense features, followed by a voxel-wise local-global aggregation of enhanced features.
  arXiv  Detail & Related papers  (2024-06-20T17:47:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.