Dimensionality reduced cortical features and their use in predicting longitudinal changes in Alzheimer's disease

Hyunjin Park, Jin ju Yang, Jongbum Seo, Jong min Lee

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Neuroimaging features derived from the cortical surface provide important information in detecting changes related to the progression of Alzheimer's disease (AD). Recent widespread adoption of neuroimaging has allowed researchers to study longitudinal data in AD. We adopted cortical thickness and sulcal depth, parameterized by three-dimensional meshes, from magnetic resonance imaging as the surface features. The cortical feature is high-dimensional, and it is difficult to use directly with a classifier because of the "small sample size" problem. We applied manifold learning to reduce the dimensionality of the feature and then tested the usage of the dimensionality reduced feature with a support vector machine classifier. Principal component analysis (PCA) was chosen as the method of manifold learning. PCA was applied to a region of interest within the cortical surface. We used 30 normal, 30 mild cognitive impairment (MCI) and 12 conversion cases taken from the ADNI database. The classifier was trained using the cortical features extracted from normal and MCI patients. The classifier was tested for the 12 conversion patients only using the imaging data before the actual conversion. The conversion was predicted early with an accuracy of 83%.

Original languageEnglish
Pages (from-to)17-22
Number of pages6
JournalNeuroscience Letters
Volume550
DOIs
Publication statusPublished - 2013 Aug 29

Fingerprint

Principal Component Analysis
Neuroimaging
Alzheimer Disease
Learning
Sample Size
Longitudinal Studies
Research Personnel
Magnetic Resonance Imaging
Databases
Cognitive Dysfunction
Support Vector Machine

All Science Journal Classification (ASJC) codes

  • Neuroscience(all)

Cite this

@article{a0472a65ad154c7b9ba2c2926e6dc5b8,
title = "Dimensionality reduced cortical features and their use in predicting longitudinal changes in Alzheimer's disease",
abstract = "Neuroimaging features derived from the cortical surface provide important information in detecting changes related to the progression of Alzheimer's disease (AD). Recent widespread adoption of neuroimaging has allowed researchers to study longitudinal data in AD. We adopted cortical thickness and sulcal depth, parameterized by three-dimensional meshes, from magnetic resonance imaging as the surface features. The cortical feature is high-dimensional, and it is difficult to use directly with a classifier because of the {"}small sample size{"} problem. We applied manifold learning to reduce the dimensionality of the feature and then tested the usage of the dimensionality reduced feature with a support vector machine classifier. Principal component analysis (PCA) was chosen as the method of manifold learning. PCA was applied to a region of interest within the cortical surface. We used 30 normal, 30 mild cognitive impairment (MCI) and 12 conversion cases taken from the ADNI database. The classifier was trained using the cortical features extracted from normal and MCI patients. The classifier was tested for the 12 conversion patients only using the imaging data before the actual conversion. The conversion was predicted early with an accuracy of 83{\%}.",
author = "Hyunjin Park and Yang, {Jin ju} and Jongbum Seo and Lee, {Jong min}",
year = "2013",
month = "8",
day = "29",
doi = "10.1016/j.neulet.2013.06.042",
language = "English",
volume = "550",
pages = "17--22",
journal = "Neuroscience Letters",
issn = "0304-3940",
publisher = "Elsevier Ireland Ltd",

}

Dimensionality reduced cortical features and their use in predicting longitudinal changes in Alzheimer's disease. / Park, Hyunjin; Yang, Jin ju; Seo, Jongbum; Lee, Jong min.

In: Neuroscience Letters, Vol. 550, 29.08.2013, p. 17-22.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Dimensionality reduced cortical features and their use in predicting longitudinal changes in Alzheimer's disease

AU - Park, Hyunjin

AU - Yang, Jin ju

AU - Seo, Jongbum

AU - Lee, Jong min

PY - 2013/8/29

Y1 - 2013/8/29

N2 - Neuroimaging features derived from the cortical surface provide important information in detecting changes related to the progression of Alzheimer's disease (AD). Recent widespread adoption of neuroimaging has allowed researchers to study longitudinal data in AD. We adopted cortical thickness and sulcal depth, parameterized by three-dimensional meshes, from magnetic resonance imaging as the surface features. The cortical feature is high-dimensional, and it is difficult to use directly with a classifier because of the "small sample size" problem. We applied manifold learning to reduce the dimensionality of the feature and then tested the usage of the dimensionality reduced feature with a support vector machine classifier. Principal component analysis (PCA) was chosen as the method of manifold learning. PCA was applied to a region of interest within the cortical surface. We used 30 normal, 30 mild cognitive impairment (MCI) and 12 conversion cases taken from the ADNI database. The classifier was trained using the cortical features extracted from normal and MCI patients. The classifier was tested for the 12 conversion patients only using the imaging data before the actual conversion. The conversion was predicted early with an accuracy of 83%.

AB - Neuroimaging features derived from the cortical surface provide important information in detecting changes related to the progression of Alzheimer's disease (AD). Recent widespread adoption of neuroimaging has allowed researchers to study longitudinal data in AD. We adopted cortical thickness and sulcal depth, parameterized by three-dimensional meshes, from magnetic resonance imaging as the surface features. The cortical feature is high-dimensional, and it is difficult to use directly with a classifier because of the "small sample size" problem. We applied manifold learning to reduce the dimensionality of the feature and then tested the usage of the dimensionality reduced feature with a support vector machine classifier. Principal component analysis (PCA) was chosen as the method of manifold learning. PCA was applied to a region of interest within the cortical surface. We used 30 normal, 30 mild cognitive impairment (MCI) and 12 conversion cases taken from the ADNI database. The classifier was trained using the cortical features extracted from normal and MCI patients. The classifier was tested for the 12 conversion patients only using the imaging data before the actual conversion. The conversion was predicted early with an accuracy of 83%.

UR - http://www.scopus.com/inward/record.url?scp=84881376328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881376328&partnerID=8YFLogxK

U2 - 10.1016/j.neulet.2013.06.042

DO - 10.1016/j.neulet.2013.06.042

M3 - Article

C2 - 23827219

AN - SCOPUS:84881376328

VL - 550

SP - 17

EP - 22

JO - Neuroscience Letters

JF - Neuroscience Letters

SN - 0304-3940

ER -