Individual subject classification for Alzheimer's disease based on incremental learning using a spatial frequency representation of cortical thickness data

Youngsang Cho, Jun Kyung Seong, Yong Jeong, Sung Yong Shin

Research output: Contribution to journalArticle

99 Citations (Scopus)

Abstract

Patterns of brain atrophy measured by magnetic resonance structural imaging have been utilized as significant biomarkers for diagnosis of Alzheimer's disease (AD). However, brain atrophy is variable across patients and is non-specific for AD in general. Thus, automatic methods for AD classification require a large number of structural data due to complex and variable patterns of brain atrophy. In this paper, we propose an incremental method for AD classification using cortical thickness data. We represent the cortical thickness data of a subject in terms of their spatial frequency components, employing the manifold harmonic transform. The basis functions for this transform are obtained from the eigenfunctions of the Laplace-Beltrami operator, which are dependent only on the geometry of a cortical surface but not on the cortical thickness defined on it. This facilitates individual subject classification based on incremental learning. In general, methods based on region-wise features poorly reflect the detailed spatial variation of cortical thickness, and those based on vertex-wise features are sensitive to noise. Adopting a vertex-wise cortical thickness representation, our method can still achieve robustness to noise by filtering out high frequency components of the cortical thickness data while reflecting their spatial variation. This compromise leads to high accuracy in AD classification. We utilized MR volumes provided by Alzheimer's Disease Neuroimaging Initiative (ADNI) to validate the performance of the method. Our method discriminated AD patients from Healthy Control (HC) subjects with 82% sensitivity and 93% specificity. It also discriminated Mild Cognitive Impairment (MCI) patients, who converted to AD within 18. months, from non-converted MCI subjects with 63% sensitivity and 76% specificity. Moreover, it showed that the entorhinal cortex was the most discriminative region for classification, which is consistent with previous pathological findings. In comparison with other classification methods, our method demonstrated high classification performance in both categories, which supports the discriminative power of our method in both AD diagnosis and AD prediction.

Original languageEnglish
Pages (from-to)2217-2230
Number of pages14
JournalNeuroImage
Volume59
Issue number3
DOIs
Publication statusPublished - 2012 Feb 1
Externally publishedYes

Fingerprint

Alzheimer Disease
Learning
Atrophy
Noise
Brain
Sensitivity and Specificity
Entorhinal Cortex
Neuroimaging
Healthy Volunteers
Biomarkers
Magnetic Resonance Imaging

Keywords

  • Alzheimer's disease
  • Cortical thickness
  • Frequency representation
  • Incremental learning
  • Individual subject classification

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Individual subject classification for Alzheimer's disease based on incremental learning using a spatial frequency representation of cortical thickness data. / Cho, Youngsang; Seong, Jun Kyung; Jeong, Yong; Shin, Sung Yong.

In: NeuroImage, Vol. 59, No. 3, 01.02.2012, p. 2217-2230.

Research output: Contribution to journalArticle

@article{ee1beb12fbf1400db959b0f3d099e476,
title = "Individual subject classification for Alzheimer's disease based on incremental learning using a spatial frequency representation of cortical thickness data",
abstract = "Patterns of brain atrophy measured by magnetic resonance structural imaging have been utilized as significant biomarkers for diagnosis of Alzheimer's disease (AD). However, brain atrophy is variable across patients and is non-specific for AD in general. Thus, automatic methods for AD classification require a large number of structural data due to complex and variable patterns of brain atrophy. In this paper, we propose an incremental method for AD classification using cortical thickness data. We represent the cortical thickness data of a subject in terms of their spatial frequency components, employing the manifold harmonic transform. The basis functions for this transform are obtained from the eigenfunctions of the Laplace-Beltrami operator, which are dependent only on the geometry of a cortical surface but not on the cortical thickness defined on it. This facilitates individual subject classification based on incremental learning. In general, methods based on region-wise features poorly reflect the detailed spatial variation of cortical thickness, and those based on vertex-wise features are sensitive to noise. Adopting a vertex-wise cortical thickness representation, our method can still achieve robustness to noise by filtering out high frequency components of the cortical thickness data while reflecting their spatial variation. This compromise leads to high accuracy in AD classification. We utilized MR volumes provided by Alzheimer's Disease Neuroimaging Initiative (ADNI) to validate the performance of the method. Our method discriminated AD patients from Healthy Control (HC) subjects with 82{\%} sensitivity and 93{\%} specificity. It also discriminated Mild Cognitive Impairment (MCI) patients, who converted to AD within 18. months, from non-converted MCI subjects with 63{\%} sensitivity and 76{\%} specificity. Moreover, it showed that the entorhinal cortex was the most discriminative region for classification, which is consistent with previous pathological findings. In comparison with other classification methods, our method demonstrated high classification performance in both categories, which supports the discriminative power of our method in both AD diagnosis and AD prediction.",
keywords = "Alzheimer's disease, Cortical thickness, Frequency representation, Incremental learning, Individual subject classification",
author = "Youngsang Cho and Seong, {Jun Kyung} and Yong Jeong and Shin, {Sung Yong}",
year = "2012",
month = "2",
day = "1",
doi = "10.1016/j.neuroimage.2011.09.085",
language = "English",
volume = "59",
pages = "2217--2230",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "3",

}

TY - JOUR

T1 - Individual subject classification for Alzheimer's disease based on incremental learning using a spatial frequency representation of cortical thickness data

AU - Cho, Youngsang

AU - Seong, Jun Kyung

AU - Jeong, Yong

AU - Shin, Sung Yong

PY - 2012/2/1

Y1 - 2012/2/1

N2 - Patterns of brain atrophy measured by magnetic resonance structural imaging have been utilized as significant biomarkers for diagnosis of Alzheimer's disease (AD). However, brain atrophy is variable across patients and is non-specific for AD in general. Thus, automatic methods for AD classification require a large number of structural data due to complex and variable patterns of brain atrophy. In this paper, we propose an incremental method for AD classification using cortical thickness data. We represent the cortical thickness data of a subject in terms of their spatial frequency components, employing the manifold harmonic transform. The basis functions for this transform are obtained from the eigenfunctions of the Laplace-Beltrami operator, which are dependent only on the geometry of a cortical surface but not on the cortical thickness defined on it. This facilitates individual subject classification based on incremental learning. In general, methods based on region-wise features poorly reflect the detailed spatial variation of cortical thickness, and those based on vertex-wise features are sensitive to noise. Adopting a vertex-wise cortical thickness representation, our method can still achieve robustness to noise by filtering out high frequency components of the cortical thickness data while reflecting their spatial variation. This compromise leads to high accuracy in AD classification. We utilized MR volumes provided by Alzheimer's Disease Neuroimaging Initiative (ADNI) to validate the performance of the method. Our method discriminated AD patients from Healthy Control (HC) subjects with 82% sensitivity and 93% specificity. It also discriminated Mild Cognitive Impairment (MCI) patients, who converted to AD within 18. months, from non-converted MCI subjects with 63% sensitivity and 76% specificity. Moreover, it showed that the entorhinal cortex was the most discriminative region for classification, which is consistent with previous pathological findings. In comparison with other classification methods, our method demonstrated high classification performance in both categories, which supports the discriminative power of our method in both AD diagnosis and AD prediction.

AB - Patterns of brain atrophy measured by magnetic resonance structural imaging have been utilized as significant biomarkers for diagnosis of Alzheimer's disease (AD). However, brain atrophy is variable across patients and is non-specific for AD in general. Thus, automatic methods for AD classification require a large number of structural data due to complex and variable patterns of brain atrophy. In this paper, we propose an incremental method for AD classification using cortical thickness data. We represent the cortical thickness data of a subject in terms of their spatial frequency components, employing the manifold harmonic transform. The basis functions for this transform are obtained from the eigenfunctions of the Laplace-Beltrami operator, which are dependent only on the geometry of a cortical surface but not on the cortical thickness defined on it. This facilitates individual subject classification based on incremental learning. In general, methods based on region-wise features poorly reflect the detailed spatial variation of cortical thickness, and those based on vertex-wise features are sensitive to noise. Adopting a vertex-wise cortical thickness representation, our method can still achieve robustness to noise by filtering out high frequency components of the cortical thickness data while reflecting their spatial variation. This compromise leads to high accuracy in AD classification. We utilized MR volumes provided by Alzheimer's Disease Neuroimaging Initiative (ADNI) to validate the performance of the method. Our method discriminated AD patients from Healthy Control (HC) subjects with 82% sensitivity and 93% specificity. It also discriminated Mild Cognitive Impairment (MCI) patients, who converted to AD within 18. months, from non-converted MCI subjects with 63% sensitivity and 76% specificity. Moreover, it showed that the entorhinal cortex was the most discriminative region for classification, which is consistent with previous pathological findings. In comparison with other classification methods, our method demonstrated high classification performance in both categories, which supports the discriminative power of our method in both AD diagnosis and AD prediction.

KW - Alzheimer's disease

KW - Cortical thickness

KW - Frequency representation

KW - Incremental learning

KW - Individual subject classification

UR - http://www.scopus.com/inward/record.url?scp=84855418467&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855418467&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2011.09.085

DO - 10.1016/j.neuroimage.2011.09.085

M3 - Article

C2 - 22008371

AN - SCOPUS:84855418467

VL - 59

SP - 2217

EP - 2230

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 3

ER -