Cargando…
Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer’s dementia diagnosis using multi-measure rs-fMRI spatial patterns
BACKGROUND: Early diagnosis of Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) is essential for timely treatment. Machine learning and multivariate pattern analysis (MVPA) for the diagnosis of brain disorders are explicitly attracting attention in the neuroimaging community. In this pap...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6386400/ https://www.ncbi.nlm.nih.gov/pubmed/30794629 http://dx.doi.org/10.1371/journal.pone.0212582 |
_version_ | 1783397377862795264 |
---|---|
author | Nguyen, Duc Thanh Ryu, Seungjun Qureshi, Muhammad Naveed Iqbal Choi, Min Lee, Kun Ho Lee, Boreom |
author_facet | Nguyen, Duc Thanh Ryu, Seungjun Qureshi, Muhammad Naveed Iqbal Choi, Min Lee, Kun Ho Lee, Boreom |
author_sort | Nguyen, Duc Thanh |
collection | PubMed |
description | BACKGROUND: Early diagnosis of Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) is essential for timely treatment. Machine learning and multivariate pattern analysis (MVPA) for the diagnosis of brain disorders are explicitly attracting attention in the neuroimaging community. In this paper, we propose a voxel-wise discriminative framework applied to multi-measure resting-state fMRI (rs-fMRI) that integrates hybrid MVPA and extreme learning machine (ELM) for the automated discrimination of AD and MCI from the cognitive normal (CN) state. MATERIALS AND METHODS: We used two rs-fMRI cohorts: the public Alzheimer’s disease Neuroimaging Initiative database (ADNI2) and an in-house Alzheimer’s disease cohort from South Korea, both including individuals with AD, MCI, and normal controls. After extracting three-dimensional (3-D) patterns measuring regional coherence and functional connectivity during the resting state, we performed univariate statistical t-tests to generate a 3-D mask that retained only voxels showing significant changes. Given the initial univariate features, to enhance discriminative patterns, we implemented MVPA feature reduction using support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO), in combination with the univariate t-test. Classifications were performed by an ELM, and its efficiency was compared to linear and nonlinear (radial basis function) SVMs. RESULTS: The maximal accuracies achieved by the method in the ADNI2 cohort were 98.86% (p<0.001) and 98.57% (p<0.001) for AD and MCI vs. CN, respectively. In the in-house cohort, the same accuracies were 98.70% (p<0.001) and 94.16% (p<0.001). CONCLUSION: From a clinical perspective, combining extreme learning machine and hybrid MVPA applied on concatenations of multiple rs-fMRI biomarkers can potentially assist the clinicians in AD and MCI diagnosis. |
format | Online Article Text |
id | pubmed-6386400 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-63864002019-03-09 Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer’s dementia diagnosis using multi-measure rs-fMRI spatial patterns Nguyen, Duc Thanh Ryu, Seungjun Qureshi, Muhammad Naveed Iqbal Choi, Min Lee, Kun Ho Lee, Boreom PLoS One Research Article BACKGROUND: Early diagnosis of Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) is essential for timely treatment. Machine learning and multivariate pattern analysis (MVPA) for the diagnosis of brain disorders are explicitly attracting attention in the neuroimaging community. In this paper, we propose a voxel-wise discriminative framework applied to multi-measure resting-state fMRI (rs-fMRI) that integrates hybrid MVPA and extreme learning machine (ELM) for the automated discrimination of AD and MCI from the cognitive normal (CN) state. MATERIALS AND METHODS: We used two rs-fMRI cohorts: the public Alzheimer’s disease Neuroimaging Initiative database (ADNI2) and an in-house Alzheimer’s disease cohort from South Korea, both including individuals with AD, MCI, and normal controls. After extracting three-dimensional (3-D) patterns measuring regional coherence and functional connectivity during the resting state, we performed univariate statistical t-tests to generate a 3-D mask that retained only voxels showing significant changes. Given the initial univariate features, to enhance discriminative patterns, we implemented MVPA feature reduction using support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO), in combination with the univariate t-test. Classifications were performed by an ELM, and its efficiency was compared to linear and nonlinear (radial basis function) SVMs. RESULTS: The maximal accuracies achieved by the method in the ADNI2 cohort were 98.86% (p<0.001) and 98.57% (p<0.001) for AD and MCI vs. CN, respectively. In the in-house cohort, the same accuracies were 98.70% (p<0.001) and 94.16% (p<0.001). CONCLUSION: From a clinical perspective, combining extreme learning machine and hybrid MVPA applied on concatenations of multiple rs-fMRI biomarkers can potentially assist the clinicians in AD and MCI diagnosis. Public Library of Science 2019-02-22 /pmc/articles/PMC6386400/ /pubmed/30794629 http://dx.doi.org/10.1371/journal.pone.0212582 Text en © 2019 Nguyen 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 Nguyen, Duc Thanh Ryu, Seungjun Qureshi, Muhammad Naveed Iqbal Choi, Min Lee, Kun Ho Lee, Boreom Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer’s dementia diagnosis using multi-measure rs-fMRI spatial patterns |
title | Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer’s dementia diagnosis using multi-measure rs-fMRI spatial patterns |
title_full | Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer’s dementia diagnosis using multi-measure rs-fMRI spatial patterns |
title_fullStr | Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer’s dementia diagnosis using multi-measure rs-fMRI spatial patterns |
title_full_unstemmed | Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer’s dementia diagnosis using multi-measure rs-fMRI spatial patterns |
title_short | Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer’s dementia diagnosis using multi-measure rs-fMRI spatial patterns |
title_sort | hybrid multivariate pattern analysis combined with extreme learning machine for alzheimer’s dementia diagnosis using multi-measure rs-fmri spatial patterns |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6386400/ https://www.ncbi.nlm.nih.gov/pubmed/30794629 http://dx.doi.org/10.1371/journal.pone.0212582 |
work_keys_str_mv | AT nguyenducthanh hybridmultivariatepatternanalysiscombinedwithextremelearningmachineforalzheimersdementiadiagnosisusingmultimeasurersfmrispatialpatterns AT ryuseungjun hybridmultivariatepatternanalysiscombinedwithextremelearningmachineforalzheimersdementiadiagnosisusingmultimeasurersfmrispatialpatterns AT qureshimuhammadnaveediqbal hybridmultivariatepatternanalysiscombinedwithextremelearningmachineforalzheimersdementiadiagnosisusingmultimeasurersfmrispatialpatterns AT choimin hybridmultivariatepatternanalysiscombinedwithextremelearningmachineforalzheimersdementiadiagnosisusingmultimeasurersfmrispatialpatterns AT leekunho hybridmultivariatepatternanalysiscombinedwithextremelearningmachineforalzheimersdementiadiagnosisusingmultimeasurersfmrispatialpatterns AT leeboreom hybridmultivariatepatternanalysiscombinedwithextremelearningmachineforalzheimersdementiadiagnosisusingmultimeasurersfmrispatialpatterns |