Unsupervised Denoising of Diffusion-Weighted Images with Bias and Variance Corrected Noise Modeling

• URL: http://arxiv.org/abs/2602.22235v1
• Date: Sun, 22 Feb 2026 04:32:21 GMT
• Title: Unsupervised Denoising of Diffusion-Weighted Images with Bias and Variance Corrected Noise Modeling
• Authors: Jine Xie, Zhicheng Zhang, Yunwei Chen, Yanqiu Feng, Xinyuan Zhang,
• Abstract summary: Diffusion magnetic resonance imaging (dMRI) plays a vital role in both clinical diagnostics and neuroscience research.<n>Recent self-supervised and unsupervised denoising methods offer a practical solution by enhancing image quality without requiring clean references.<n>However, most of these methods do not explicitly account for the non-Gaussian noise characteristics commonly present in dMRI magnitude data during the supervised learning process.<n>We introduce noise-corrected training objectives that explicitly model Rician statistics. Specifically, we propose two alternative loss functions: one derived from the first-order moment to remove mean bias, and another from the second-order moment to correct squared-
• Score: 19.01755888772832
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion magnetic resonance imaging (dMRI) plays a vital role in both clinical diagnostics and neuroscience research. However, its inherently low signal-to-noise ratio (SNR), especially under high diffusion weighting, significantly degrades image quality and impairs downstream analysis. Recent self-supervised and unsupervised denoising methods offer a practical solution by enhancing image quality without requiring clean references. However, most of these methods do not explicitly account for the non-Gaussian noise characteristics commonly present in dMRI magnitude data during the supervised learning process, potentially leading to systematic bias and heteroscedastic variance, particularly under low-SNR conditions. To overcome this limitation, we introduce noise-corrected training objectives that explicitly model Rician statistics. Specifically, we propose two alternative loss functions: one derived from the first-order moment to remove mean bias, and another from the second-order moment to correct squared-signal bias. Both losses include adaptive weighting to account for variance heterogeneity and can be used without changing the network architecture. These objectives are instantiated in an image-specific, unsupervised Deep Image Prior (DIP) framework. Comprehensive experiments on simulated and in-vivo dMRI show that the proposed losses effectively reduce Rician bias and suppress noise fluctuations, yielding higher image quality and more reliable diffusion metrics than state-of-the-art denoising baselines. These results underscore the importance of bias- and variance-aware noise modeling for robust dMRI analysis under low-SNR conditions.

Related papers

• 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)
• Score-based Self-supervised MRI Denoising [1.6385815610837167]
  Supervised learning based denoising approaches have achieved impressive performance but require high signal-to-noise ratio (SNR) labels.<n>Self-supervised learning holds promise to address the label scarcity issue, but existing self-supervised denoising methods tend to oversmooth fine spatial features.<n>We introduce Corruption2Self (C2S), a novel score-based self-supervised framework for MRI denoising.
  arXiv  Detail & Related papers  (2025-05-08T20:27:13Z)
• Noise Level Adaptive Diffusion Model for Robust Reconstruction of Accelerated MRI [34.361078452552945]
  Real-world MRI acquisitions already contain inherent noise due to thermal fluctuations. We propose a posterior sampling strategy with a novel NoIse Level Adaptive Data Consistency (Nila-DC) operation. Our method surpasses the state-of-the-art MRI reconstruction methods, and is highly robust against various noise levels.
  arXiv  Detail & Related papers  (2024-03-08T12:07:18Z)
• Denoising Simulated Low-Field MRI (70mT) using Denoising Autoencoders (DAE) and Cycle-Consistent Generative Adversarial Networks (Cycle-GAN) [68.8204255655161]
  Cycle Consistent Generative Adversarial Network (GAN) is implemented to yield high-field, high resolution, high signal-to-noise ratio (SNR) Magnetic Resonance Imaging (MRI) images. Images were utilized to train a Denoising Autoencoder (DAE) and a Cycle-GAN, with paired and unpaired cases. This work demonstrates the use of a generative deep learning model that can outperform classical DAEs to improve low-field MRI images and does not require image pairs.
  arXiv  Detail & Related papers  (2023-07-12T00:01:00Z)
• Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling [56.506240377714754]
  We present a novel strategy called the Diffusion Model for Image Denoising (DMID) Our strategy includes an adaptive embedding method that embeds the noisy image into a pre-trained unconditional diffusion model. Our DMID strategy achieves state-of-the-art performance on both distortion-based and perception-based metrics.
  arXiv  Detail & Related papers  (2023-07-08T14:59:41Z)
• On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis [58.634791552376235]
  Deep Learning (DL) models have achieved state-of-the-art performance in diagnosing multiple diseases using reconstructed images as input. DL models are sensitive to varying artifacts as it leads to changes in the input data distribution between the training and testing phases. We propose to use other normalization techniques, such as Group Normalization and Layer Normalization, to inject robustness into model performance against varying image artifacts.
  arXiv  Detail & Related papers  (2023-06-23T03:09:03Z)
• Deep Ultrasound Denoising Using Diffusion Probabilistic Models [5.828784149537374]
  Previous denoising methods often remove the speckles, which could be informative for radiologists and also for quantitative ultrasound. Herein, a method based on the recent Denoising Diffusion Probabilistic Models (DDPM) is proposed. It iteratively enhances the image quality by eliminating the noise while preserving the speckle texture.
  arXiv  Detail & Related papers  (2023-06-12T21:53:32Z)
• The role of noise in denoising models for anomaly detection in medical images [62.0532151156057]
  Pathological brain lesions exhibit diverse appearance in brain images. Unsupervised anomaly detection approaches have been proposed using only normal data for training. We show that optimization of the spatial resolution and magnitude of the noise improves the performance of different model training regimes.
  arXiv  Detail & Related papers  (2023-01-19T21:39:38Z)
• SAR Despeckling using a Denoising Diffusion Probabilistic Model [52.25981472415249]
  The presence of speckle degrades the image quality and adversely affects the performance of SAR image understanding applications. We introduce SAR-DDPM, a denoising diffusion probabilistic model for SAR despeckling. The proposed method achieves significant improvements in both quantitative and qualitative results over the state-of-the-art despeckling methods.
  arXiv  Detail & Related papers  (2022-06-09T14:00:26Z)
• Negligible effect of brain MRI data preprocessing for tumor segmentation [36.89606202543839]
  We conduct experiments on three publicly available datasets and evaluate the effect of different preprocessing steps in deep neural networks. Our results demonstrate that most popular standardization steps add no value to the network performance. We suggest that image intensity normalization approaches do not contribute to model accuracy because of the reduction of signal variance with image standardization.
  arXiv  Detail & Related papers  (2022-04-11T17:29:36Z)
• Zero-shot Blind Image Denoising via Implicit Neural Representations [77.79032012459243]
  We propose an alternative denoising strategy that leverages the architectural inductive bias of implicit neural representations (INRs) We show that our method outperforms existing zero-shot denoising methods under an extensive set of low-noise or real-noise scenarios.
  arXiv  Detail & Related papers  (2022-04-05T12:46:36Z)
• MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion [38.62448918459113]
  We propose a new denoising method based on score-based reverse diffusion sampling. Our network, trained only with coronal knee scans, excels even on out-of-distribution in vivo liver MRI data.
  arXiv  Detail & Related papers  (2022-03-23T10:35:06Z)

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.