Cargando…

Evaluation of MRI Denoising Methods Using Unsupervised Learning

In this paper we evaluate two unsupervised approaches to denoise Magnetic Resonance Images (MRI) in the complex image space using the raw information that k-space holds. The first method is based on Stein’s Unbiased Risk Estimator, while the second approach is based on a blindspot network, which lim...

Descripción completa

Detalles Bibliográficos
Autores principales: Moreno López, Marc, Frederick, Joshua M., Ventura, Jonathan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8212039/
https://www.ncbi.nlm.nih.gov/pubmed/34151253
http://dx.doi.org/10.3389/frai.2021.642731
_version_ 1783709596718727168
author Moreno López, Marc
Frederick, Joshua M.
Ventura, Jonathan
author_facet Moreno López, Marc
Frederick, Joshua M.
Ventura, Jonathan
author_sort Moreno López, Marc
collection PubMed
description In this paper we evaluate two unsupervised approaches to denoise Magnetic Resonance Images (MRI) in the complex image space using the raw information that k-space holds. The first method is based on Stein’s Unbiased Risk Estimator, while the second approach is based on a blindspot network, which limits the network’s receptive field. Both methods are tested on two different datasets, one containing real knee MRI and the other consists of synthetic brain MRI. These datasets contain information about the complex image space which will be used for denoising purposes. Both networks are compared against a state-of-the-art algorithm, Non-Local Means (NLM) using quantitative and qualitative measures. For most given metrics and qualitative measures, both networks outperformed NLM, and they prove to be reliable denoising methods.
format Online
Article
Text
id pubmed-8212039
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-82120392021-06-19 Evaluation of MRI Denoising Methods Using Unsupervised Learning Moreno López, Marc Frederick, Joshua M. Ventura, Jonathan Front Artif Intell Artificial Intelligence In this paper we evaluate two unsupervised approaches to denoise Magnetic Resonance Images (MRI) in the complex image space using the raw information that k-space holds. The first method is based on Stein’s Unbiased Risk Estimator, while the second approach is based on a blindspot network, which limits the network’s receptive field. Both methods are tested on two different datasets, one containing real knee MRI and the other consists of synthetic brain MRI. These datasets contain information about the complex image space which will be used for denoising purposes. Both networks are compared against a state-of-the-art algorithm, Non-Local Means (NLM) using quantitative and qualitative measures. For most given metrics and qualitative measures, both networks outperformed NLM, and they prove to be reliable denoising methods. Frontiers Media S.A. 2021-06-04 /pmc/articles/PMC8212039/ /pubmed/34151253 http://dx.doi.org/10.3389/frai.2021.642731 Text en Copyright © 2021 Moreno López, Frederick and Ventura. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Artificial Intelligence
Moreno López, Marc
Frederick, Joshua M.
Ventura, Jonathan
Evaluation of MRI Denoising Methods Using Unsupervised Learning
title Evaluation of MRI Denoising Methods Using Unsupervised Learning
title_full Evaluation of MRI Denoising Methods Using Unsupervised Learning
title_fullStr Evaluation of MRI Denoising Methods Using Unsupervised Learning
title_full_unstemmed Evaluation of MRI Denoising Methods Using Unsupervised Learning
title_short Evaluation of MRI Denoising Methods Using Unsupervised Learning
title_sort evaluation of mri denoising methods using unsupervised learning
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8212039/
https://www.ncbi.nlm.nih.gov/pubmed/34151253
http://dx.doi.org/10.3389/frai.2021.642731
work_keys_str_mv AT morenolopezmarc evaluationofmridenoisingmethodsusingunsupervisedlearning
AT frederickjoshuam evaluationofmridenoisingmethodsusingunsupervisedlearning
AT venturajonathan evaluationofmridenoisingmethodsusingunsupervisedlearning