Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Rician Denoising Diffusion Probabilistic Models For Sodium Breast MRI Enhancement

Shuaiyu Yuan, Tristan Whitmarsh, Dimitri A Kessler, Otso Arponen, Mary A McLean, Gabrielle Baxter, Frank Riemer, Aneurin J Kennerley, William J Brackenbury, Fiona J Gilbert, Joshua D Kaggie

TL;DR

The Rician Denoising Diffusion Probabilistic Models (RDDPM) is introduced by introducing the Rician Denoising Diffusion Probabilistic Models (RDDPM) for sodium MRI denoising, where RDDPM consistently outperforms DDPM and other CNN-based denoising methods.

Abstract

Sodium MRI is an imaging technique used to visualize and quantify sodium concentrations in vivo, playing a role in many biological processes and potentially aiding in breast cancer characterization. Sodium MRI, however, suffers from inherently low signal-to-noise ratios (SNR) and spatial resolution, compared with conventional proton MRI. A deep-learning method, the Denoising Diffusion Probabilistic Models (DDPM), has demonstrated success across a wide range of denoising tasks, yet struggles with sodium MRI's unique noise profile, as DDPM primarily targets Gaussian noise. DDPM can distort features when applied to sodium MRI. This paper advances the DDPM by introducing the Rician Denoising Diffusion Probabilistic Models (RDDPM) for sodium MRI denoising. RDDPM converts Rician noise to Gaussian noise at each timestep during the denoising process. The model's performance is evaluated using three non-reference image quality assessment metrics, where RDDPM consistently outperforms DDPM and other CNN-based denoising methods.

Rician Denoising Diffusion Probabilistic Models For Sodium Breast MRI Enhancement

TL;DR

The Rician Denoising Diffusion Probabilistic Models (RDDPM) is introduced by introducing the Rician Denoising Diffusion Probabilistic Models (RDDPM) for sodium MRI denoising, where RDDPM consistently outperforms DDPM and other CNN-based denoising methods.

Abstract

Sodium MRI is an imaging technique used to visualize and quantify sodium concentrations in vivo, playing a role in many biological processes and potentially aiding in breast cancer characterization. Sodium MRI, however, suffers from inherently low signal-to-noise ratios (SNR) and spatial resolution, compared with conventional proton MRI. A deep-learning method, the Denoising Diffusion Probabilistic Models (DDPM), has demonstrated success across a wide range of denoising tasks, yet struggles with sodium MRI's unique noise profile, as DDPM primarily targets Gaussian noise. DDPM can distort features when applied to sodium MRI. This paper advances the DDPM by introducing the Rician Denoising Diffusion Probabilistic Models (RDDPM) for sodium MRI denoising. RDDPM converts Rician noise to Gaussian noise at each timestep during the denoising process. The model's performance is evaluated using three non-reference image quality assessment metrics, where RDDPM consistently outperforms DDPM and other CNN-based denoising methods.

Paper Structure

This paper contains 15 sections, 4 equations, 3 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. Method
  3. Sodium MRI Denoising with CNN
  4. DDPM
  5. Sodium MRI Denoising with RDDPM
  6. Evaluation
  7. Experiments
  8. Data
  9. Implementation
  10. Results and Discussion
  11. Denoising Results of DDPM and RDDPM
  12. Comparison of Denoised Results
  13. Conclusion
  14. Compliance with Ethical Standards
  15. Acknowledgements

Figures (3)

  • Figure 1: The pipeline of proposed RDDPM. (a) aims to convert the image with Rician noise to Gaussian noise at each timestep. (b) is a pre-trained DDPM.
  • Figure 2: An example of a sodium MR image prior to DL denoising, and the corresponding denoising results from DDPM and RDDPM. Two ROIs (a) and a yellow line (b) are selected and magnified for better comparison.
  • Figure 3: An example of a sodium MR image and the corresponding denoising results from BM3D, DnCNN, Unet, Resunet, ADNet, DDPM and RDDPM. A ROI (a) and a yellow line (b) are selected and magnified.