Zero-Shot Recon2Recon: Data-Free Unsupervised Denoiser Learning for Plug-and-Play Magnetic Resonance Imaging Reconstruction

This work presents a novel zero-shot learning method for undersampled magnetic resonance imaging (MRI) reconstruction. The proposed method utilizes a plug-and-play approach, wherein the denoiser neural network, serving as the image prior, is trained solely with the single acquired undersampled k-spa...

Full description

Saved in:
Bibliographic Details
Main Author: Tae Hyung Kim
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10933922/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849388520313978880
author Tae Hyung Kim
author_facet Tae Hyung Kim
author_sort Tae Hyung Kim
collection DOAJ
description This work presents a novel zero-shot learning method for undersampled magnetic resonance imaging (MRI) reconstruction. The proposed method utilizes a plug-and-play approach, wherein the denoiser neural network, serving as the image prior, is trained solely with the single acquired undersampled k-space data. Specifically, the training of the denoiser employs the Noise2Noise and Self2Self frameworks; the acquired k-space is divided into two disjoint subsets using complementary subsampling masks, which are then reconstructed to serve as the training data and target labels, respectively. We provide theoretical justification for the proposed method, demonstrating the feasibility of training an effective denoiser without the need for extra training data or fully sampled ground truths. The trained denoiser is subsequently utilized as a plug-and-play denoiser for undersampled MRI reconstruction. We have evaluated and compared the performance of our method with several other reconstruction techniques, thereby demonstrating the advantages of the proposed approach.
format Article
id doaj-art-908982b432b140de915bbdd39e5d6098
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-908982b432b140de915bbdd39e5d60982025-08-20T03:42:15ZengIEEEIEEE Access2169-35362025-01-0113505905060210.1109/ACCESS.2025.355285310933922Zero-Shot Recon2Recon: Data-Free Unsupervised Denoiser Learning for Plug-and-Play Magnetic Resonance Imaging ReconstructionTae Hyung Kim0https://orcid.org/0000-0001-5881-7265Department of Computer Engineering, Hongik University, Seoul, Republic of KoreaThis work presents a novel zero-shot learning method for undersampled magnetic resonance imaging (MRI) reconstruction. The proposed method utilizes a plug-and-play approach, wherein the denoiser neural network, serving as the image prior, is trained solely with the single acquired undersampled k-space data. Specifically, the training of the denoiser employs the Noise2Noise and Self2Self frameworks; the acquired k-space is divided into two disjoint subsets using complementary subsampling masks, which are then reconstructed to serve as the training data and target labels, respectively. We provide theoretical justification for the proposed method, demonstrating the feasibility of training an effective denoiser without the need for extra training data or fully sampled ground truths. The trained denoiser is subsequently utilized as a plug-and-play denoiser for undersampled MRI reconstruction. We have evaluated and compared the performance of our method with several other reconstruction techniques, thereby demonstrating the advantages of the proposed approach.https://ieeexplore.ieee.org/document/10933922/Magnetic resonance imaginginverse problemsimage reconstructiondenoisingplug-and-play methods
spellingShingle Tae Hyung Kim
Zero-Shot Recon2Recon: Data-Free Unsupervised Denoiser Learning for Plug-and-Play Magnetic Resonance Imaging Reconstruction
IEEE Access
Magnetic resonance imaging
inverse problems
image reconstruction
denoising
plug-and-play methods
title Zero-Shot Recon2Recon: Data-Free Unsupervised Denoiser Learning for Plug-and-Play Magnetic Resonance Imaging Reconstruction
title_full Zero-Shot Recon2Recon: Data-Free Unsupervised Denoiser Learning for Plug-and-Play Magnetic Resonance Imaging Reconstruction
title_fullStr Zero-Shot Recon2Recon: Data-Free Unsupervised Denoiser Learning for Plug-and-Play Magnetic Resonance Imaging Reconstruction
title_full_unstemmed Zero-Shot Recon2Recon: Data-Free Unsupervised Denoiser Learning for Plug-and-Play Magnetic Resonance Imaging Reconstruction
title_short Zero-Shot Recon2Recon: Data-Free Unsupervised Denoiser Learning for Plug-and-Play Magnetic Resonance Imaging Reconstruction
title_sort zero shot recon2recon data free unsupervised denoiser learning for plug and play magnetic resonance imaging reconstruction
topic Magnetic resonance imaging
inverse problems
image reconstruction
denoising
plug-and-play methods
url https://ieeexplore.ieee.org/document/10933922/
work_keys_str_mv AT taehyungkim zeroshotrecon2recondatafreeunsuperviseddenoiserlearningforplugandplaymagneticresonanceimagingreconstruction