Recycling diagnostic MRI for empowering brain morphometric research – Critical & practical assessment on learning-based image super-resolution

Preliminary studies have shown the feasibility of deep learning (DL)-based super-resolution (SR) technique for reconstructing thick-slice/gap diagnostic MR images into high-resolution isotropic data, which would be of great significance for brain research field if the vast amount of diagnostic MRI d...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Gaoping Liu, Zehong Cao, Qiang Xu, Qirui Zhang, Fang Yang, Xinyu Xie, Jingru Hao, Yinghuan Shi, Boris C. Bernhardt, Yichu He, Feng Shi, Guangming Lu, Zhiqiang Zhang
Formato: article
Lenguaje:EN
Publicado: Elsevier 2021
Materias:
Acceso en línea:https://doaj.org/article/ff567b0fdbc84ce991ece2a84fce771a
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:ff567b0fdbc84ce991ece2a84fce771a
record_format dspace
spelling oai:doaj.org-article:ff567b0fdbc84ce991ece2a84fce771a2021-11-04T04:26:47ZRecycling diagnostic MRI for empowering brain morphometric research – Critical & practical assessment on learning-based image super-resolution1095-957210.1016/j.neuroimage.2021.118687https://doaj.org/article/ff567b0fdbc84ce991ece2a84fce771a2021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1053811921009605https://doaj.org/toc/1095-9572Preliminary studies have shown the feasibility of deep learning (DL)-based super-resolution (SR) technique for reconstructing thick-slice/gap diagnostic MR images into high-resolution isotropic data, which would be of great significance for brain research field if the vast amount of diagnostic MRI data could be successively put into brain morphometric study. However, less evidence has addressed the practicability of the strategy, because lack of a large-sample available real data for constructing DL model. In this work, we employed a large cohort (n = 2052) of peculiar data with both low through-plane resolution diagnostic and high-resolution isotropic brain MR images from identical subjects. By leveraging a series of SR approaches, including a proposed novel DL algorithm of Structure Constrained Super Resolution Network (SCSRN), the diagnostic images were transformed to high-resolution isotropic data to meet the criteria of brain research in voxel-based and surface-based morphometric analyses. We comprehensively assessed image quality and the practicability of the reconstructed data in a variety of morphometric analysis scenarios. We further compared the performance of SR approaches to the ground truth high-resolution isotropic data. The results showed (i) DL-based SR algorithms generally improve the quality of diagnostic images and render morphometric analysis more accurate, especially, with the most superior performance of the novel approach of SCSRN. (ii) Accuracies vary across brain structures and methods, and (iii) performance increases were higher for voxel than for surface based approaches. This study supports that DL-based image super-resolution potentially recycle huge amount of routine diagnostic brain MRI deposited in sleeping state, and turning them into useful data for neurometric research.Gaoping LiuZehong CaoQiang XuQirui ZhangFang YangXinyu XieJingru HaoYinghuan ShiBoris C. BernhardtYichu HeFeng ShiGuangming LuZhiqiang ZhangElsevierarticleDeep-learningImage super-resolutionBrain MRIMorphometric analysisPractical assessmentNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENNeuroImage, Vol 245, Iss , Pp 118687- (2021)
institution DOAJ
collection DOAJ
language EN
topic Deep-learning
Image super-resolution
Brain MRI
Morphometric analysis
Practical assessment
Neurosciences. Biological psychiatry. Neuropsychiatry
RC321-571
spellingShingle Deep-learning
Image super-resolution
Brain MRI
Morphometric analysis
Practical assessment
Neurosciences. Biological psychiatry. Neuropsychiatry
RC321-571
Gaoping Liu
Zehong Cao
Qiang Xu
Qirui Zhang
Fang Yang
Xinyu Xie
Jingru Hao
Yinghuan Shi
Boris C. Bernhardt
Yichu He
Feng Shi
Guangming Lu
Zhiqiang Zhang
Recycling diagnostic MRI for empowering brain morphometric research – Critical & practical assessment on learning-based image super-resolution
description Preliminary studies have shown the feasibility of deep learning (DL)-based super-resolution (SR) technique for reconstructing thick-slice/gap diagnostic MR images into high-resolution isotropic data, which would be of great significance for brain research field if the vast amount of diagnostic MRI data could be successively put into brain morphometric study. However, less evidence has addressed the practicability of the strategy, because lack of a large-sample available real data for constructing DL model. In this work, we employed a large cohort (n = 2052) of peculiar data with both low through-plane resolution diagnostic and high-resolution isotropic brain MR images from identical subjects. By leveraging a series of SR approaches, including a proposed novel DL algorithm of Structure Constrained Super Resolution Network (SCSRN), the diagnostic images were transformed to high-resolution isotropic data to meet the criteria of brain research in voxel-based and surface-based morphometric analyses. We comprehensively assessed image quality and the practicability of the reconstructed data in a variety of morphometric analysis scenarios. We further compared the performance of SR approaches to the ground truth high-resolution isotropic data. The results showed (i) DL-based SR algorithms generally improve the quality of diagnostic images and render morphometric analysis more accurate, especially, with the most superior performance of the novel approach of SCSRN. (ii) Accuracies vary across brain structures and methods, and (iii) performance increases were higher for voxel than for surface based approaches. This study supports that DL-based image super-resolution potentially recycle huge amount of routine diagnostic brain MRI deposited in sleeping state, and turning them into useful data for neurometric research.
format article
author Gaoping Liu
Zehong Cao
Qiang Xu
Qirui Zhang
Fang Yang
Xinyu Xie
Jingru Hao
Yinghuan Shi
Boris C. Bernhardt
Yichu He
Feng Shi
Guangming Lu
Zhiqiang Zhang
author_facet Gaoping Liu
Zehong Cao
Qiang Xu
Qirui Zhang
Fang Yang
Xinyu Xie
Jingru Hao
Yinghuan Shi
Boris C. Bernhardt
Yichu He
Feng Shi
Guangming Lu
Zhiqiang Zhang
author_sort Gaoping Liu
title Recycling diagnostic MRI for empowering brain morphometric research – Critical & practical assessment on learning-based image super-resolution
title_short Recycling diagnostic MRI for empowering brain morphometric research – Critical & practical assessment on learning-based image super-resolution
title_full Recycling diagnostic MRI for empowering brain morphometric research – Critical & practical assessment on learning-based image super-resolution
title_fullStr Recycling diagnostic MRI for empowering brain morphometric research – Critical & practical assessment on learning-based image super-resolution
title_full_unstemmed Recycling diagnostic MRI for empowering brain morphometric research – Critical & practical assessment on learning-based image super-resolution
title_sort recycling diagnostic mri for empowering brain morphometric research – critical & practical assessment on learning-based image super-resolution
publisher Elsevier
publishDate 2021
url https://doaj.org/article/ff567b0fdbc84ce991ece2a84fce771a
work_keys_str_mv AT gaopingliu recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT zehongcao recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT qiangxu recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT qiruizhang recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT fangyang recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT xinyuxie recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT jingruhao recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT yinghuanshi recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT boriscbernhardt recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT yichuhe recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT fengshi recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT guangminglu recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
AT zhiqiangzhang recyclingdiagnosticmriforempoweringbrainmorphometricresearchcriticalamppracticalassessmentonlearningbasedimagesuperresolution
_version_ 1718445310958632960