Self-supervised learning for denoising of multidimensional MRI data

Cited 1 time in webofscience Cited 0 time in scopus
  • Hit : 45
  • Download : 0
PurposeTo develop a fast denoising framework for high-dimensional MRI data based on a self-supervised learning scheme, which does not require ground truth clean image.Theory and MethodsQuantitative MRI faces limitations in SNR, because the variation of signal amplitude in a large set of images is the key mechanism for quantification. In addition, the complex non-linear signal models make the fitting process vulnerable to noise. To address these issues, we propose a fast deep-learning framework for denoising, which efficiently exploits the redundancy in multidimensional MRI data. A self-supervised model was designed to use only noisy images for training, bypassing the challenge of clean data paucity in clinical practice. For validation, we used two different datasets of simulated magnetization transfer contrast MR fingerprinting (MTC-MRF) dataset and in vivo DWI image dataset to show the generalizability.ResultsThe proposed method drastically improved denoising performance in the presence of mild-to-severe noise regardless of noise distributions compared to previous methods of the BM3D, tMPPCA, and Patch2self. The improvements were even pronounced in the following quantification results from the denoised images.ConclusionThe proposed MD-S2S (Multidimensional-Self2Self) denoising technique could be further applied to various multi-dimensional MRI data and improve the quantification accuracy of tissue parameter maps.
Publisher
WILEY
Issue Date
2024-11
Language
English
Article Type
Article
Citation

MAGNETIC RESONANCE IN MEDICINE, v.92, no.5, pp.1980 - 1994

ISSN
0740-3194
DOI
10.1002/mrm.30197
URI
http://hdl.handle.net/10203/322922
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 1 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0