MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusionopen access
- Authors
- Chung, H.; Lee, E.S.; Ye, J.C.
- Issue Date
- Apr-2023
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Denoising; Diffusion model; Diffusion processes; Magnetic resonance imaging; Mathematical models; MRI; Noise measurement; Noise reduction; Numerical models; Stochastic contraction; Training
- Citation
- IEEE Transactions on Medical Imaging, v.42, no.4, pp 1 - 1
- Pages
- 1
- Journal Title
- IEEE Transactions on Medical Imaging
- Volume
- 42
- Number
- 4
- Start Page
- 1
- End Page
- 1
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/68631
- DOI
- 10.1109/TMI.2022.3220681
- ISSN
- 0278-0062
1558-254X
- Abstract
- Patient scans from MRI often suffer from noise, which hampers the diagnostic capability of such images. As a method to mitigate such artifact, denoising is largely studied both within the medical imaging community and beyond the community as a general subject. However, recent deep neural network-based approaches mostly rely on the minimum mean squared error (MMSE) estimates, which tend to produce a blurred output. Moreover, such models suffer when deployed in real-world sitautions: out-of-distribution data, and complex noise distributions that deviate from the usual parametric noise models. In this work, we propose a new denoising method based on score-based reverse diffusion sampling, which overcomes all the aforementioned drawbacks. Our network, trained only with coronal knee scans, excels even on out-of-distribution <italic>in vivo</italic> liver MRI data, contaminated with complex mixture of noise. Even more, we propose a method to enhance the resolution of the denoised image with the <italic>same</italic> network. With extensive experiments, we show that our method establishes state-of-the-art performance, while having desirable properties which prior MMSE denoisers did not have: flexibly choosing the extent of denoising, and quantifying uncertainty. IEEE
- Files in This Item
-
- Appears in
Collections - ETC > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.