# Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning

arXiv: https://arxiv.org/abs/2011.01355 · HTML: https://mlsanity.com/paper/2011.01355/

## Key facts

- Cited by 29 papers in the map (data through 14 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.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 12 of 12)

- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks](https://mlsanity.com/paper/1406.6909/) (2014)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [Deep K-SVD Denoising](https://mlsanity.com/paper/1909.13164/) (2019)
- [Linearized Kernel Dictionary Learning](https://mlsanity.com/paper/1509.05634/) (2015)
- [Non Local Spatial and Angular Matching : Enabling higher spatial resolution diffusion MRI datasets through adaptive denoising](https://mlsanity.com/paper/1606.07239/) (2016)
- [Trainlets: Dictionary Learning in High Dimensions](https://mlsanity.com/paper/1602.00212/) (2016)
- [Improving Fiber Alignment in HARDI by Combining Contextual PDE Flow with Constrained Spherical Deconvolution](https://mlsanity.com/paper/1506.07062/) (2015)

## Built on by (most cited first, 29 of 29)

- [MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion](https://mlsanity.com/paper/2203.12621/) (2022)
- [DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model](https://mlsanity.com/paper/2112.05149/) (2021)
- [DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models](https://mlsanity.com/paper/2302.03018/) (2023)
- [Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review](https://mlsanity.com/paper/2308.00247/) (2023)
- [SDnDTI: Self-supervised deep learning-based denoising for diffusion tensor MRI](https://mlsanity.com/paper/2111.07220/) (2021)
- [Spatio-Angular Convolutions for Super-resolution in Diffusion MRI](https://mlsanity.com/paper/2306.00854/) (2023)
- [Diffusion MRI with Machine Learning](https://mlsanity.com/paper/2402.00019/) (2024)
- [Learning to Assimilate in Chaotic Dynamical Systems](https://mlsanity.com/paper/2111.01058/) (2021)
- [Score-based Self-supervised MRI Denoising](https://mlsanity.com/paper/2505.05631/) (2025)
- [Angular Super-Resolution in Diffusion MRI with a 3D Recurrent Convolutional Autoencoder](https://mlsanity.com/paper/2203.15598/) (2022)
- [A Comparison of Image Denoising Methods](https://mlsanity.com/paper/2304.08990/) (2023)
- [Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement](https://mlsanity.com/paper/2501.13514/) (2025)
- [Field-of-View Extension for Brain Diffusion MRI via Deep Generative Models](https://mlsanity.com/paper/2405.03652/) (2024)
- [DiffDenoise: Self-Supervised Medical Image Denoising with Conditional Diffusion Models](https://mlsanity.com/paper/2504.00264/) (2025)
- [Multi-Modality Conditioned Variational U-Net for Field-of-View Extension in Brain Diffusion MRI](https://mlsanity.com/paper/2409.13846/) (2024)
- [Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography Angiography](https://mlsanity.com/paper/2202.10360/) (2022)
- [Supervised Denoising of Diffusion-Weighted Magnetic Resonance Images Using a Convolutional Neural Network and Transfer Learning](https://mlsanity.com/paper/2206.00305/) (2022)
- [Generative AI for Rapid Diffusion MRI with Improved Image Quality, Reliability and Generalizability](https://mlsanity.com/paper/2303.05686/) (2023)
- [Equivariant spatio-hemispherical networks for diffusion MRI deconvolution](https://mlsanity.com/paper/2411.11819/) (2024)
- [NUQ: A Noise Metric for Diffusion MRI via Uncertainty Discrepancy Quantification](https://mlsanity.com/paper/2203.01921/) (2022)
- [Speckle Image Restoration without Clean Data](https://mlsanity.com/paper/2205.08833/) (2022)
- [Self-supervised training of deep denoisers in multi-coil MRI considering noise correlations](https://mlsanity.com/paper/2208.07552/) (2022)
- [Reliable Deep Diffusion Tensor Estimation: Rethinking the Power of Data-Driven Optimization Routine](https://mlsanity.com/paper/2409.02492/) (2024)
- [MBD: Multi b-value Denoising of Diffusion Magnetic Resonance Images](https://mlsanity.com/paper/2410.16898/) (2024)
- [MID: A Self-supervised Multimodal Iterative Denoising Framework](https://mlsanity.com/paper/2511.00997/) (2025)
- [RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference](https://mlsanity.com/paper/2604.15459/) (2026)
- [CoilDrop-MRI: Self-supervised physics-guided MRI reconstruction with coil dropout](https://mlsanity.com/paper/2606.00100/) (2026)
- [NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling](https://mlsanity.com/paper/2606.23200/) (2026)
- [dMRI-F: A Foundation Model for Generalizable Diffusion MRI Analysis from Sparse Acquisitions](https://mlsanity.com/paper/2610.17968/) (2026)

## 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.