Cargando…

Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging

Patches from three orthogonal views of selected cerebral regions can be utilized to learn convolutional neural network (CNN) models for staging the Alzheimer disease (AD) spectrum including preclinical AD, mild cognitive impairment due to AD, and dementia due to AD and normal controls. Hippocampi, a...

Descripción completa

Detalles Bibliográficos
Autores principales: Ahmed, Samsuddin, Kim, Byeong C., Lee, Kun Ho, Jung, Ho Yub
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7723284/
https://www.ncbi.nlm.nih.gov/pubmed/33290403
http://dx.doi.org/10.1371/journal.pone.0242712
_version_ 1783620313119981568
author Ahmed, Samsuddin
Kim, Byeong C.
Lee, Kun Ho
Jung, Ho Yub
author_facet Ahmed, Samsuddin
Kim, Byeong C.
Lee, Kun Ho
Jung, Ho Yub
author_sort Ahmed, Samsuddin
collection PubMed
description Patches from three orthogonal views of selected cerebral regions can be utilized to learn convolutional neural network (CNN) models for staging the Alzheimer disease (AD) spectrum including preclinical AD, mild cognitive impairment due to AD, and dementia due to AD and normal controls. Hippocampi, amygdalae and insulae were selected from the volumetric analysis of structured magnetic resonance images (MRIs). Three-view patches (TVPs) from these regions were fed to the CNN for training. MRIs were classified with the SoftMax-normalized scores of individual model predictions on TVPs. The significance of each region of interest (ROI) for staging the AD spectrum was evaluated and reported. The results of the ensemble classifier are compared with state-of-the-art methods using the same evaluation metrics. Patch-based ROI ensembles provide comparable diagnostic performance for AD staging. In this work, TVP-based ROI analysis using a CNN provides informative landmarks in cerebral MRIs and may have significance in clinical studies and computer-aided diagnosis system design.
format Online
Article
Text
id pubmed-7723284
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-77232842020-12-16 Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging Ahmed, Samsuddin Kim, Byeong C. Lee, Kun Ho Jung, Ho Yub PLoS One Research Article Patches from three orthogonal views of selected cerebral regions can be utilized to learn convolutional neural network (CNN) models for staging the Alzheimer disease (AD) spectrum including preclinical AD, mild cognitive impairment due to AD, and dementia due to AD and normal controls. Hippocampi, amygdalae and insulae were selected from the volumetric analysis of structured magnetic resonance images (MRIs). Three-view patches (TVPs) from these regions were fed to the CNN for training. MRIs were classified with the SoftMax-normalized scores of individual model predictions on TVPs. The significance of each region of interest (ROI) for staging the AD spectrum was evaluated and reported. The results of the ensemble classifier are compared with state-of-the-art methods using the same evaluation metrics. Patch-based ROI ensembles provide comparable diagnostic performance for AD staging. In this work, TVP-based ROI analysis using a CNN provides informative landmarks in cerebral MRIs and may have significance in clinical studies and computer-aided diagnosis system design. Public Library of Science 2020-12-08 /pmc/articles/PMC7723284/ /pubmed/33290403 http://dx.doi.org/10.1371/journal.pone.0242712 Text en © 2020 Ahmed et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Ahmed, Samsuddin
Kim, Byeong C.
Lee, Kun Ho
Jung, Ho Yub
Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging
title Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging
title_full Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging
title_fullStr Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging
title_full_unstemmed Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging
title_short Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging
title_sort ensemble of roi-based convolutional neural network classifiers for staging the alzheimer disease spectrum from magnetic resonance imaging
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7723284/
https://www.ncbi.nlm.nih.gov/pubmed/33290403
http://dx.doi.org/10.1371/journal.pone.0242712
work_keys_str_mv AT ahmedsamsuddin ensembleofroibasedconvolutionalneuralnetworkclassifiersforstagingthealzheimerdiseasespectrumfrommagneticresonanceimaging
AT kimbyeongc ensembleofroibasedconvolutionalneuralnetworkclassifiersforstagingthealzheimerdiseasespectrumfrommagneticresonanceimaging
AT leekunho ensembleofroibasedconvolutionalneuralnetworkclassifiersforstagingthealzheimerdiseasespectrumfrommagneticresonanceimaging
AT junghoyub ensembleofroibasedconvolutionalneuralnetworkclassifiersforstagingthealzheimerdiseasespectrumfrommagneticresonanceimaging
AT ensembleofroibasedconvolutionalneuralnetworkclassifiersforstagingthealzheimerdiseasespectrumfrommagneticresonanceimaging