Hierarchical fusion of features and classifier decisions for Alzheimer's disease diagnosis

Manhua Liu, Daoqiang Zhang, Dinggang Shen

Research output: Contribution to journalArticle

47 Citations (Scopus)

Abstract

Pattern classification methods have been widely investigated for analysis of brain images to assist the diagnosis of Alzheimer's disease (AD) and its early stage such as mild cognitive impairment (MCI). By considering the nature of pathological changes, a large number of features related to both local brain regions and interbrain regions can be extracted for classification. However, it is challenging to design a single global classifier to integrate all these features for effective classification, due to the issue of small sample size. To this end, we propose a hierarchical ensemble classification method to combine multilevel classifiers by gradually integrating a large number of features from both local brain regions and interbrain regions. Thus, the large-scale classification problem can be divided into a set of small-scale and easier-to-solve problems in a bottom-up and local-to-global fashion, for more accurate classification. To demonstrate its performance, we use the spatially normalized grey matter (GM) of each MR brain image as imaging features. Specifically, we first partition the whole brain image into a number of local brain regions and, for each brain region, we build two low-level classifiers to transform local imaging features and the inter-region correlations into high-level features. Then, we generate multiple high-level classifiers, with each evaluating the high-level features from the respective brain regions. Finally, we combine the outputs of all high-level classifiers for making a final classification. Our method has been evaluated using the baseline MR images of 652 subjects (including 198 AD patients, 225 MCI patients, and 229 normal controls (NC)) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our classification method can achieve the accuracies of 92.0% and 85.3% for classifications of AD versus NC and MCI versus NC, respectively, demonstrating very promising classification performance compared to the state-of-the-art classification methods.

Original languageEnglish
Pages (from-to)1305-1319
Number of pages15
JournalHuman Brain Mapping
Volume35
Issue number4
DOIs
Publication statusPublished - 2014 Jan 1
Externally publishedYes

Fingerprint

Alzheimer Disease
Brain
Diencephalon
Neuroimaging
Sample Size
Databases

Keywords

  • Alzheimer's disease
  • Brain disease diagnosis
  • Hierarchical classification
  • Local patch
  • Mild cognitive impairment (MCI)
  • SVM classifier

ASJC Scopus subject areas

  • Anatomy
  • Neurology
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology
  • Clinical Neurology

Cite this

Hierarchical fusion of features and classifier decisions for Alzheimer's disease diagnosis. / Liu, Manhua; Zhang, Daoqiang; Shen, Dinggang.

In: Human Brain Mapping, Vol. 35, No. 4, 01.01.2014, p. 1305-1319.

Research output: Contribution to journalArticle

@article{c7d8b700843d4d0181be34b925013238,
title = "Hierarchical fusion of features and classifier decisions for Alzheimer's disease diagnosis",
abstract = "Pattern classification methods have been widely investigated for analysis of brain images to assist the diagnosis of Alzheimer's disease (AD) and its early stage such as mild cognitive impairment (MCI). By considering the nature of pathological changes, a large number of features related to both local brain regions and interbrain regions can be extracted for classification. However, it is challenging to design a single global classifier to integrate all these features for effective classification, due to the issue of small sample size. To this end, we propose a hierarchical ensemble classification method to combine multilevel classifiers by gradually integrating a large number of features from both local brain regions and interbrain regions. Thus, the large-scale classification problem can be divided into a set of small-scale and easier-to-solve problems in a bottom-up and local-to-global fashion, for more accurate classification. To demonstrate its performance, we use the spatially normalized grey matter (GM) of each MR brain image as imaging features. Specifically, we first partition the whole brain image into a number of local brain regions and, for each brain region, we build two low-level classifiers to transform local imaging features and the inter-region correlations into high-level features. Then, we generate multiple high-level classifiers, with each evaluating the high-level features from the respective brain regions. Finally, we combine the outputs of all high-level classifiers for making a final classification. Our method has been evaluated using the baseline MR images of 652 subjects (including 198 AD patients, 225 MCI patients, and 229 normal controls (NC)) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our classification method can achieve the accuracies of 92.0{\%} and 85.3{\%} for classifications of AD versus NC and MCI versus NC, respectively, demonstrating very promising classification performance compared to the state-of-the-art classification methods.",
keywords = "Alzheimer's disease, Brain disease diagnosis, Hierarchical classification, Local patch, Mild cognitive impairment (MCI), SVM classifier",
author = "Manhua Liu and Daoqiang Zhang and Dinggang Shen",
year = "2014",
month = "1",
day = "1",
doi = "10.1002/hbm.22254",
language = "English",
volume = "35",
pages = "1305--1319",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",
number = "4",

}

TY - JOUR

T1 - Hierarchical fusion of features and classifier decisions for Alzheimer's disease diagnosis

AU - Liu, Manhua

AU - Zhang, Daoqiang

AU - Shen, Dinggang

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Pattern classification methods have been widely investigated for analysis of brain images to assist the diagnosis of Alzheimer's disease (AD) and its early stage such as mild cognitive impairment (MCI). By considering the nature of pathological changes, a large number of features related to both local brain regions and interbrain regions can be extracted for classification. However, it is challenging to design a single global classifier to integrate all these features for effective classification, due to the issue of small sample size. To this end, we propose a hierarchical ensemble classification method to combine multilevel classifiers by gradually integrating a large number of features from both local brain regions and interbrain regions. Thus, the large-scale classification problem can be divided into a set of small-scale and easier-to-solve problems in a bottom-up and local-to-global fashion, for more accurate classification. To demonstrate its performance, we use the spatially normalized grey matter (GM) of each MR brain image as imaging features. Specifically, we first partition the whole brain image into a number of local brain regions and, for each brain region, we build two low-level classifiers to transform local imaging features and the inter-region correlations into high-level features. Then, we generate multiple high-level classifiers, with each evaluating the high-level features from the respective brain regions. Finally, we combine the outputs of all high-level classifiers for making a final classification. Our method has been evaluated using the baseline MR images of 652 subjects (including 198 AD patients, 225 MCI patients, and 229 normal controls (NC)) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our classification method can achieve the accuracies of 92.0% and 85.3% for classifications of AD versus NC and MCI versus NC, respectively, demonstrating very promising classification performance compared to the state-of-the-art classification methods.

AB - Pattern classification methods have been widely investigated for analysis of brain images to assist the diagnosis of Alzheimer's disease (AD) and its early stage such as mild cognitive impairment (MCI). By considering the nature of pathological changes, a large number of features related to both local brain regions and interbrain regions can be extracted for classification. However, it is challenging to design a single global classifier to integrate all these features for effective classification, due to the issue of small sample size. To this end, we propose a hierarchical ensemble classification method to combine multilevel classifiers by gradually integrating a large number of features from both local brain regions and interbrain regions. Thus, the large-scale classification problem can be divided into a set of small-scale and easier-to-solve problems in a bottom-up and local-to-global fashion, for more accurate classification. To demonstrate its performance, we use the spatially normalized grey matter (GM) of each MR brain image as imaging features. Specifically, we first partition the whole brain image into a number of local brain regions and, for each brain region, we build two low-level classifiers to transform local imaging features and the inter-region correlations into high-level features. Then, we generate multiple high-level classifiers, with each evaluating the high-level features from the respective brain regions. Finally, we combine the outputs of all high-level classifiers for making a final classification. Our method has been evaluated using the baseline MR images of 652 subjects (including 198 AD patients, 225 MCI patients, and 229 normal controls (NC)) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our classification method can achieve the accuracies of 92.0% and 85.3% for classifications of AD versus NC and MCI versus NC, respectively, demonstrating very promising classification performance compared to the state-of-the-art classification methods.

KW - Alzheimer's disease

KW - Brain disease diagnosis

KW - Hierarchical classification

KW - Local patch

KW - Mild cognitive impairment (MCI)

KW - SVM classifier

UR - http://www.scopus.com/inward/record.url?scp=84896396327&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896396327&partnerID=8YFLogxK

U2 - 10.1002/hbm.22254

DO - 10.1002/hbm.22254

M3 - Article

C2 - 23417832

AN - SCOPUS:84896396327

VL - 35

SP - 1305

EP - 1319

JO - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 4

ER -