mlsanityData to 14 Oct 2026

Speckle2Self: Self-Supervised Ultrasound Speckle Reduction Without Clean Data

arXiv 2507.06828 ↗First posted 9 Jul 2025eess.IV cs.AI cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Image denoising is a fundamental task in computer vision, particularly in medical ultrasound (US) imaging, where speckle noise significantly degrades image quality. Although recent advancements in deep neural networks have led to substantial improvements in denoising for natural images, these methods cannot be directly applied to US speckle noise, as it is not purely random. Instead, US speckle arises from complex wave interference within the body microstructure, making it tissue-dependent. This dependency means that obtaining two independent noisy observations of the same scene, as required by pioneering Noise2Noise, is not feasible. Additionally, blind-spot networks also cannot handle US speckle noise due to its high spatial dependency. To address this challenge, we introduce Speckle2Self, a novel self-supervised algorithm for speckle reduction using only single noisy observations. The key insight is that applying a multi-scale perturbation (MSP) operation introduces tissue-dependent variations in the speckle pattern across different scales, while preserving the shared anatomical structure. This enables effective speckle suppression by modeling the clean image as a low-rank signal and isolating the sparse noise component. To demonstrate its effectiveness, Speckle2Self is comprehensively compared with conventional filter-based denoising algorithms and SOTA learning-based methods, using both realistic simulated US images and human carotid US images. Additionally, data from multiple US machines are employed to evaluate model generalization and adaptability to images from unseen domains. Project page: https://noseefood.github.io/us-speckle2self/

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 40 of its 91 references that are in the map. First posted on arXiv 9 Jul 2025.

Builds on

40 of 91 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  5. 2017Deep Image Priorcited by 1,098
  6. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 533
  7. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 364
  8. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 276
  9. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
  10. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  11. 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 173
  12. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
28 more
  1. 2018Neural Nearest Neighbors Networkscited by 98
  2. 2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 93
  3. 2020Unpaired Learning of Deep Image Denoisingcited by 74
  4. 2024Towards Generalizable Tumor Synthesiscited by 65
  5. 2017Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimizationcited by 35
  6. 2023Robotic Ultrasound Imaging: State-of-the-Art and Future Perspectivescited by 31
  7. 2021Cross-modal Attention for MRI and Ultrasound Volume Registrationcited by 21
  8. 2023MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalizationcited by 18
  9. 2023Dehazing Ultrasound using Diffusion Modelscited by 17
  10. 2024Machine Learning in Robotic Ultrasound Imaging: Challenges and Perspectivescited by 17
  11. 2024Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidancecited by 17
  12. 2020So you think you can DAS? A viewpoint on delay-and-sum beamformingcited by 14
  13. 2021Deformation-Aware Robotic 3D Ultrasoundcited by 14
  14. 2023Intelligent Robotic Sonographer: Mutual Information-based Disentangled Reward Learning from Few Demonstrationscited by 14
  15. 2023Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Networkcited by 12
  16. 2023Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimizationcited by 10
  17. 2023Motion Magnification in Robotic Sonography: Enabling Pulsation-Aware Artery Segmentationcited by 9
  18. 2023DefCor-Net: Physics-Aware Ultrasound Deformation Correctioncited by 8
  19. 2021SIMUS: an open-source simulator for medical ultrasound imaging. Part I: theory & examplescited by 7
  20. 2022Deep Ultrasound Denoising Without Clean Datacited by 6
  21. 2023Mitigating Aberration-Induced Noise: A Deep Learning-Based Aberration-to-Aberration Approachcited by 5
  22. 2024VibNet: Vibration-Boosted Needle Detection in Ultrasound Imagescited by 5
  23. 2024Class-Aware Cartilage Segmentation for Autonomous US-CT Registration in Robotic Intercostal Ultrasound Imagingcited by 5
  24. 2025UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptationcited by 5
  25. 2023Deep Coherence Learning: An Unsupervised Deep Beamformer for High Quality Single Plane Wave Imaging in Medical Ultrasoundcited by 4
  26. 2024Synomaly Noise and Multi-Stage Diffusion: A Novel Approach for Unsupervised Anomaly Detection in Medical Imagescited by 3
  27. 2023Ultrafast Cardiac Imaging Using Deep Learning For Speckle-Tracking Echocardiographycited by 2
  28. 2025Lightweight Physics-Aware Zero-Shot Ultrasound Plane-Wave Denoisingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 9.

9 papers.

  1. 2026Adversarial Robustness of Deep Learning-Based Thyroid Nodule Segmentation in Ultrasoundcited by 0
  2. 2026IRSDE-Despeckle: A Physics-Grounded Diffusion Model for Generalizable Ultrasound Despecklingcited by 0
  3. 2026Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoisingcited by 0
  4. 2026Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zoomingcited by 0
  5. 2026Noise-Aware Boundary-Enhanced Generative Learning for Ultrasound Speckle Reductioncited by 0
  6. 2026UltraPIPS: Improving model perception in B-mode ultrasound with foundation modelscited by 0
  7. 2026Null-Space Diffusion Restoration with Adaptive Uncertainty-Guided Fusion for Ultrasound Speckle Reductioncited by 0
  8. 2026Scanning While Imagining: A Scene-Graph World Model for Robotic Ultrasound Navigationcited by 0
  9. 2026Mask2Restore: Self-Supervised Ultrasound Despeckling via Inpaintingcited by 0