mlsanityData to 7 Oct 2026

Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning

arXiv 2011.01355 ↗First posted 2 Nov 2020cs.LG cs.CV q-bio.QMcited by 28

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Diffusion-weighted magnetic resonance imaging (DWI) is the only noninvasive method for quantifying microstructure and reconstructing white-matter pathways in the living human brain. Fluctuations from multiple sources create significant additive noise in DWI data which must be suppressed before subsequent microstructure analysis. We introduce a self-supervised learning method for denoising DWI data, Patch2Self, which uses the entire volume to learn a full-rank locally linear denoiser for that volume. By taking advantage of the oversampled q-space of DWI data, Patch2Self can separate structure from noise without requiring an explicit model for either. We demonstrate the effectiveness of Patch2Self via quantitative and qualitative improvements in microstructure modeling, tracking (via fiber bundle coherency) and model estimation relative to other unsupervised methods on real and simulated data.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 12 of its 48 references that are in the map. First posted on arXiv 2 Nov 2020.

Builds on

12 of 48 references.

References · 12

  1. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  2. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  3. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  4. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  5. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 299
  6. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  7. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
  8. 2019Deep K-SVD Denoisingcited by 26
  9. 2015Linearized Kernel Dictionary Learningcited by 5
  10. 2016Non Local Spatial and Angular Matching : Enabling higher spatial resolution diffusion MRI datasets through adaptive denoisingcited by 5
  11. 2016Trainlets: Dictionary Learning in High Dimensionscited by 4
  12. 2015Improving Fiber Alignment in HARDI by Combining Contextual PDE Flow with Constrained Spherical Deconvolutioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 7; 2023: 5; 2024: 6; 2025: 4; 2026: 3.

28 papers.

Sort:

By area:

  1. 2022MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusioncited by 66
  2. 2021DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Modelcited by 57
  3. 2023DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Modelscited by 50
  4. 2023Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Reviewcited by 17
  5. 2021SDnDTI: Self-supervised deep learning-based denoising for diffusion tensor MRIcited by 16
  6. 2024Diffusion MRI with Machine Learningcited by 11
  7. 2021Learning to Assimilate in Chaotic Dynamical Systemscited by 10
  8. 2023Spatio-Angular Convolutions for Super-resolution in Diffusion MRIcited by 10
  9. 2022Angular Super-Resolution in Diffusion MRI with a 3D Recurrent Convolutional Autoencodercited by 7
  10. 2023A Comparison of Image Denoising Methodscited by 7
  11. 2025Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinementcited by 6
  12. 2025Score-based Self-supervised MRI Denoisingcited by 6
16 more
  1. 2024Field-of-View Extension for Brain Diffusion MRI via Deep Generative Modelscited by 4
  2. 2025DiffDenoise: Self-Supervised Medical Image Denoising with Conditional Diffusion Modelscited by 3
  3. 2022Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography Angiographycited by 1
  4. 2022Supervised Denoising of Diffusion-Weighted Magnetic Resonance Images Using a Convolutional Neural Network and Transfer Learningcited by 1
  5. 2023Generative AI for Rapid Diffusion MRI with Improved Image Quality, Reliability and Generalizabilitycited by 1
  6. 2024Multi-Modality Conditioned Variational U-Net for Field-of-View Extension in Brain Diffusion MRIcited by 1
  7. 2024Equivariant spatio-hemispherical networks for diffusion MRI deconvolutioncited by 1
  8. 2022NUQ: A Noise Metric for Diffusion MRI via Uncertainty Discrepancy Quantificationcited by 0
  9. 2022Speckle Image Restoration without Clean Datacited by 0
  10. 2022Self-supervised training of deep denoisers in multi-coil MRI considering noise correlationscited by 0
  11. 2024Reliable Deep Diffusion Tensor Estimation: Rethinking the Power of Data-Driven Optimization Routinecited by 0
  12. 2024MBD: Multi b-value Denoising of Diffusion Magnetic Resonance Imagescited by 0
  13. 2025MID: A Self-supervised Multimodal Iterative Denoising Frameworkcited by 0
  14. 2026RelativeFlow: Taming Medical Image Denoising Learning with Noisy Referencecited by 0
  15. 2026CoilDrop-MRI: Self-supervised physics-guided MRI reconstruction with coil dropoutcited by 0
  16. 2026NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Samplingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
  2. 2025Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstruction
  3. 2025A Self-supervised Diffusion Bridge for MRI Reconstruction
  4. 20253D Anatomical Structure-guided Deep Learning for Accurate Diffusion Microstructure Imaging
  5. 2025Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising
  6. 2024On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction
  7. 2024White Matter Geometry-Guided Score-Based Diffusion Model for Tissue Microstructure Imputation in Tractography Imaging
  8. 2025DDTracking: A Deep Generative Framework for Diffusion MRI Tractography with Streamline Local-Global Spatiotemporal Modeling