# SDnDTI: Self-supervised deep learning-based denoising for diffusion tensor MRI

arXiv: https://arxiv.org/abs/2111.07220 · HTML: https://mlsanity.com/paper/2111.07220/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 128 references that are in the map.
- First posted on arXiv 14 Nov 2021.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Medical image denoising using convolutional denoising autoencoders](https://mlsanity.com/paper/1608.04667/) (2016)
- [Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning](https://mlsanity.com/paper/2011.01355/) (2020)
- [Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network](https://mlsanity.com/paper/1712.08726/) (2017)
- [A Deep Learning Approach to Denoise Optical Coherence Tomography Images of the Optic Nerve Head](https://mlsanity.com/paper/1809.10589/) (2018)
- [MRI denoising using Deep Learning and Non-local averaging](https://mlsanity.com/paper/1911.04798/) (2019)
- [Non Local Spatial and Angular Matching : Enabling higher spatial resolution diffusion MRI datasets through adaptive denoising](https://mlsanity.com/paper/1606.07239/) (2016)
- [High-fidelity, high-isotropic resolution diffusion imaging through gSlider acquisition with B1+ & T1 corrections and integrated DeltaB0/Rx shim array](https://mlsanity.com/paper/1811.05473/) (2018)

## Built on by (most cited first, 16 of 16)

- [Diffusion MRI with Machine Learning](https://mlsanity.com/paper/2402.00019/) (2024)
- [Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation: A Comprehensive Review](https://mlsanity.com/paper/2302.11089/) (2023)
- [Field-of-View Extension for Brain Diffusion MRI via Deep Generative Models](https://mlsanity.com/paper/2405.03652/) (2024)
- [Multi-Modality Conditioned Variational U-Net for Field-of-View Extension in Brain Diffusion MRI](https://mlsanity.com/paper/2409.13846/) (2024)
- [Supervised Denoising of Diffusion-Weighted Magnetic Resonance Images Using a Convolutional Neural Network and Transfer Learning](https://mlsanity.com/paper/2206.00305/) (2022)
- [Low-rank Tensor Assisted K-space Generative Model for Parallel Imaging Reconstruction](https://mlsanity.com/paper/2212.05503/) (2022)
- [Generative AI for Rapid Diffusion MRI with Improved Image Quality, Reliability and Generalizability](https://mlsanity.com/paper/2303.05686/) (2023)
- [High-Resolution Reference Image Assisted Volumetric Super-Resolution of Cardiac Diffusion Weighted Imaging](https://mlsanity.com/paper/2310.20389/) (2023)
- [Self-supervised training of deep denoisers in multi-coil MRI considering noise correlations](https://mlsanity.com/paper/2208.07552/) (2022)
- [MBD: Multi b-value Denoising of Diffusion Magnetic Resonance Images](https://mlsanity.com/paper/2410.16898/) (2024)
- [Untrained Perceptual Loss for image denoising of line-like structures in MR images](https://mlsanity.com/paper/2411.05884/) (2024)
- [3D Anatomical Structure-guided Deep Learning for Accurate Diffusion Microstructure Imaging](https://mlsanity.com/paper/2502.17933/) (2025)
- [Enhancing Diffusion-Weighted Images (DWI) for Diffusion MRI: Is it Enough without Non-Diffusion-Weighted B=0 Reference?](https://mlsanity.com/paper/2505.12978/) (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)
- [Realistic noise synthesis reduces bias and improves tissue microstructure estimation with supervised machine learning](https://mlsanity.com/paper/2606.02044/) (2026)

## Abstract (arXiv)

The noise in diffusion-weighted images (DWIs) decreases the accuracy and precision of diffusion tensor magnetic resonance imaging (DTI) derived microstructural parameters and leads to prolonged acquisition time for achieving improved signal-to-noise ratio (SNR). Deep learning-based image denoising using convolutional neural networks (CNNs) has superior performance but often requires additional high-SNR data for supervising the training of CNNs, which reduces the practical feasibility. We develop a self-supervised deep learning-based method entitled "SDnDTI" for denoising DTI data, which does not require additional high-SNR data for training. Specifically, SDnDTI divides multi-directional DTI data into many subsets, each consisting of six DWI volumes along optimally chosen diffusion-encoding directions that are robust to noise for the tensor fitting, and then synthesizes DWI volumes along all acquired directions from the diffusion tensors fitted using each subset of the data as the input data of CNNs. On the other hand, SDnDTI synthesizes DWI volumes along acquired diffusion-encoding directions with higher SNR from the diffusion tensors fitted using all acquired data as the training target. SDnDTI removes noise from each subset of synthesized DWI volumes using a deep 3-dimensional CNN to match the quality of the cleaner target DWI volumes and achieves even higher SNR by averaging all subsets of denoised data. The denoising efficacy of SDnDTI is demonstrated on two datasets provided by the Human Connectome Project (HCP) and the Lifespan HCP in Aging. The SDnDTI results preserve image sharpness and textural details and substantially improve upon those from the raw data. The results of SDnDTI are comparable to those from supervised learning-based denoising and outperform those from state-of-the-art conventional denoising algorithms including BM4D, AONLM and MPPCA.