Cargando…

FFA-DMRI: A Network Based on Feature Fusion and Attention Mechanism for Brain MRI Denoising

Magnetic Resonance Imaging (MRI) is an indispensable tool in the diagnosis of brain diseases due to painlessness and safety. Nevertheless, Rician noise is inevitably injected during the image acquisition process, which leads to poor observation and interferes with the treatment. Owing to the complex...

Descripción completa

Detalles Bibliográficos
Autores principales: Hong, Dan, Huang, Chenxi, Yang, Chenhui, Li, Jianpeng, Qian, Yunhan, Cai, Chunting
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7525046/
https://www.ncbi.nlm.nih.gov/pubmed/33041768
http://dx.doi.org/10.3389/fnins.2020.577937
_version_ 1783588660307820544
author Hong, Dan
Huang, Chenxi
Yang, Chenhui
Li, Jianpeng
Qian, Yunhan
Cai, Chunting
author_facet Hong, Dan
Huang, Chenxi
Yang, Chenhui
Li, Jianpeng
Qian, Yunhan
Cai, Chunting
author_sort Hong, Dan
collection PubMed
description Magnetic Resonance Imaging (MRI) is an indispensable tool in the diagnosis of brain diseases due to painlessness and safety. Nevertheless, Rician noise is inevitably injected during the image acquisition process, which leads to poor observation and interferes with the treatment. Owing to the complexity of Rician noise, using the elimination method of Gaussian to remove it does not perform well. Therefore, the feature fusion and attention network (FFA-DMRI) is proposed to separate noise from observed MRI. Inspired by the attention-guided CNN network (ADNet) and Convolutional block attention module (CBAM), a spatial attention mechanism has been specially designed to obtain the area of interest in MRI. Furthermore, the feature fusion block concatenates local with global information, which makes full use of the multilevel structure and boosts the expressive ability of network. The comprehensive experiments on Alzheimer’s disease neuroimaging initiative dataset (ADNI) have demonstrated high effectiveness of FFA-DMRI with maintaining the crucial brain details. Moreover, in terms of visual inspections, the denoising results are also consistent with human perception.
format Online
Article
Text
id pubmed-7525046
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-75250462020-10-09 FFA-DMRI: A Network Based on Feature Fusion and Attention Mechanism for Brain MRI Denoising Hong, Dan Huang, Chenxi Yang, Chenhui Li, Jianpeng Qian, Yunhan Cai, Chunting Front Neurosci Neuroscience Magnetic Resonance Imaging (MRI) is an indispensable tool in the diagnosis of brain diseases due to painlessness and safety. Nevertheless, Rician noise is inevitably injected during the image acquisition process, which leads to poor observation and interferes with the treatment. Owing to the complexity of Rician noise, using the elimination method of Gaussian to remove it does not perform well. Therefore, the feature fusion and attention network (FFA-DMRI) is proposed to separate noise from observed MRI. Inspired by the attention-guided CNN network (ADNet) and Convolutional block attention module (CBAM), a spatial attention mechanism has been specially designed to obtain the area of interest in MRI. Furthermore, the feature fusion block concatenates local with global information, which makes full use of the multilevel structure and boosts the expressive ability of network. The comprehensive experiments on Alzheimer’s disease neuroimaging initiative dataset (ADNI) have demonstrated high effectiveness of FFA-DMRI with maintaining the crucial brain details. Moreover, in terms of visual inspections, the denoising results are also consistent with human perception. Frontiers Media S.A. 2020-09-16 /pmc/articles/PMC7525046/ /pubmed/33041768 http://dx.doi.org/10.3389/fnins.2020.577937 Text en Copyright © 2020 Hong, Huang, Yang, Li, Qian and Cai. http://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 Neuroscience
Hong, Dan
Huang, Chenxi
Yang, Chenhui
Li, Jianpeng
Qian, Yunhan
Cai, Chunting
FFA-DMRI: A Network Based on Feature Fusion and Attention Mechanism for Brain MRI Denoising
title FFA-DMRI: A Network Based on Feature Fusion and Attention Mechanism for Brain MRI Denoising
title_full FFA-DMRI: A Network Based on Feature Fusion and Attention Mechanism for Brain MRI Denoising
title_fullStr FFA-DMRI: A Network Based on Feature Fusion and Attention Mechanism for Brain MRI Denoising
title_full_unstemmed FFA-DMRI: A Network Based on Feature Fusion and Attention Mechanism for Brain MRI Denoising
title_short FFA-DMRI: A Network Based on Feature Fusion and Attention Mechanism for Brain MRI Denoising
title_sort ffa-dmri: a network based on feature fusion and attention mechanism for brain mri denoising
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7525046/
https://www.ncbi.nlm.nih.gov/pubmed/33041768
http://dx.doi.org/10.3389/fnins.2020.577937
work_keys_str_mv AT hongdan ffadmrianetworkbasedonfeaturefusionandattentionmechanismforbrainmridenoising
AT huangchenxi ffadmrianetworkbasedonfeaturefusionandattentionmechanismforbrainmridenoising
AT yangchenhui ffadmrianetworkbasedonfeaturefusionandattentionmechanismforbrainmridenoising
AT lijianpeng ffadmrianetworkbasedonfeaturefusionandattentionmechanismforbrainmridenoising
AT qianyunhan ffadmrianetworkbasedonfeaturefusionandattentionmechanismforbrainmridenoising
AT caichunting ffadmrianetworkbasedonfeaturefusionandattentionmechanismforbrainmridenoising