Cargando…

Kernel Principal Component Analysis for dimensionality reduction in fMRI-based diagnosis of ADHD

This study explored various feature extraction methods for use in automated diagnosis of Attention-Deficit Hyperactivity Disorder (ADHD) from functional Magnetic Resonance Image (fMRI) data. Each participant's data consisted of a resting state fMRI scan as well as phenotypic data (age, gender,...

Descripción completa

Detalles Bibliográficos
Autores principales: Sidhu, Gagan S., Asgarian, Nasimeh, Greiner, Russell, Brown, Matthew R. G.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2012
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3494168/
https://www.ncbi.nlm.nih.gov/pubmed/23162439
http://dx.doi.org/10.3389/fnsys.2012.00074
_version_ 1782249371269595136
author Sidhu, Gagan S.
Asgarian, Nasimeh
Greiner, Russell
Brown, Matthew R. G.
author_facet Sidhu, Gagan S.
Asgarian, Nasimeh
Greiner, Russell
Brown, Matthew R. G.
author_sort Sidhu, Gagan S.
collection PubMed
description This study explored various feature extraction methods for use in automated diagnosis of Attention-Deficit Hyperactivity Disorder (ADHD) from functional Magnetic Resonance Image (fMRI) data. Each participant's data consisted of a resting state fMRI scan as well as phenotypic data (age, gender, handedness, IQ, and site of scanning) from the ADHD-200 dataset. We used machine learning techniques to produce support vector machine (SVM) classifiers that attempted to differentiate between (1) all ADHD patients vs. healthy controls and (2) ADHD combined (ADHD-c) type vs. ADHD inattentive (ADHD-i) type vs. controls. In different tests, we used only the phenotypic data, only the imaging data, or else both the phenotypic and imaging data. For feature extraction on fMRI data, we tested the Fast Fourier Transform (FFT), different variants of Principal Component Analysis (PCA), and combinations of FFT and PCA. PCA variants included PCA over time (PCA-t), PCA over space and time (PCA-st), and kernelized PCA (kPCA-st). Baseline chance accuracy was 64.2% produced by guessing healthy control (the majority class) for all participants. Using only phenotypic data produced 72.9% accuracy on two class diagnosis and 66.8% on three class diagnosis. Diagnosis using only imaging data did not perform as well as phenotypic-only approaches. Using both phenotypic and imaging data with combined FFT and kPCA-st feature extraction yielded accuracies of 76.0% on two class diagnosis and 68.6% on three class diagnosis—better than phenotypic-only approaches. Our results demonstrate the potential of using FFT and kPCA-st with resting-state fMRI data as well as phenotypic data for automated diagnosis of ADHD. These results are encouraging given known challenges of learning ADHD diagnostic classifiers using the ADHD-200 dataset (see Brown et al., 2012).
format Online
Article
Text
id pubmed-3494168
institution National Center for Biotechnology Information
language English
publishDate 2012
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-34941682012-11-16 Kernel Principal Component Analysis for dimensionality reduction in fMRI-based diagnosis of ADHD Sidhu, Gagan S. Asgarian, Nasimeh Greiner, Russell Brown, Matthew R. G. Front Syst Neurosci Neuroscience This study explored various feature extraction methods for use in automated diagnosis of Attention-Deficit Hyperactivity Disorder (ADHD) from functional Magnetic Resonance Image (fMRI) data. Each participant's data consisted of a resting state fMRI scan as well as phenotypic data (age, gender, handedness, IQ, and site of scanning) from the ADHD-200 dataset. We used machine learning techniques to produce support vector machine (SVM) classifiers that attempted to differentiate between (1) all ADHD patients vs. healthy controls and (2) ADHD combined (ADHD-c) type vs. ADHD inattentive (ADHD-i) type vs. controls. In different tests, we used only the phenotypic data, only the imaging data, or else both the phenotypic and imaging data. For feature extraction on fMRI data, we tested the Fast Fourier Transform (FFT), different variants of Principal Component Analysis (PCA), and combinations of FFT and PCA. PCA variants included PCA over time (PCA-t), PCA over space and time (PCA-st), and kernelized PCA (kPCA-st). Baseline chance accuracy was 64.2% produced by guessing healthy control (the majority class) for all participants. Using only phenotypic data produced 72.9% accuracy on two class diagnosis and 66.8% on three class diagnosis. Diagnosis using only imaging data did not perform as well as phenotypic-only approaches. Using both phenotypic and imaging data with combined FFT and kPCA-st feature extraction yielded accuracies of 76.0% on two class diagnosis and 68.6% on three class diagnosis—better than phenotypic-only approaches. Our results demonstrate the potential of using FFT and kPCA-st with resting-state fMRI data as well as phenotypic data for automated diagnosis of ADHD. These results are encouraging given known challenges of learning ADHD diagnostic classifiers using the ADHD-200 dataset (see Brown et al., 2012). Frontiers Media S.A. 2012-11-09 /pmc/articles/PMC3494168/ /pubmed/23162439 http://dx.doi.org/10.3389/fnsys.2012.00074 Text en Copyright © 2012 Sidhu, Asgarian, Greiner and Brown. http://www.frontiersin.org/licenseagreement This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in other forums, provided the original authors and source are credited and subject to any copyright notices concerning any third-party graphics etc.
spellingShingle Neuroscience
Sidhu, Gagan S.
Asgarian, Nasimeh
Greiner, Russell
Brown, Matthew R. G.
Kernel Principal Component Analysis for dimensionality reduction in fMRI-based diagnosis of ADHD
title Kernel Principal Component Analysis for dimensionality reduction in fMRI-based diagnosis of ADHD
title_full Kernel Principal Component Analysis for dimensionality reduction in fMRI-based diagnosis of ADHD
title_fullStr Kernel Principal Component Analysis for dimensionality reduction in fMRI-based diagnosis of ADHD
title_full_unstemmed Kernel Principal Component Analysis for dimensionality reduction in fMRI-based diagnosis of ADHD
title_short Kernel Principal Component Analysis for dimensionality reduction in fMRI-based diagnosis of ADHD
title_sort kernel principal component analysis for dimensionality reduction in fmri-based diagnosis of adhd
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3494168/
https://www.ncbi.nlm.nih.gov/pubmed/23162439
http://dx.doi.org/10.3389/fnsys.2012.00074
work_keys_str_mv AT sidhugagans kernelprincipalcomponentanalysisfordimensionalityreductioninfmribaseddiagnosisofadhd
AT asgariannasimeh kernelprincipalcomponentanalysisfordimensionalityreductioninfmribaseddiagnosisofadhd
AT greinerrussell kernelprincipalcomponentanalysisfordimensionalityreductioninfmribaseddiagnosisofadhd
AT brownmatthewrg kernelprincipalcomponentanalysisfordimensionalityreductioninfmribaseddiagnosisofadhd