Maximum-margin based representation learning from multiple atlases for Alzheimer's disease classification

Rui Min, Jian Cheng, True Price, Guorong Wu, Dinggang Shen

Research output: Chapter in Book/Report/Conference proceedingChapter

5 Citations (Scopus)

Abstract

In order to establish the correspondences between different brains for comparison, spatial normalization based morphometric measurements have been widely used in the analysis of Alzheimer's disease (AD). In the literature, different subjects are often compared in one atlas space, which may be insufficient in revealing complex brain changes. In this paper, instead of deploying one atlas for feature extraction and classification, we propose a maximum-margin based representation learning (MMRL) method to learn the optimal representation from multiple atlases. Unlike traditional methods that perform the representation learning separately from the classification, we propose to learn the new representation jointly with the classification model, which is more powerful in discriminating AD patients from normal controls (NC). We evaluated the proposed method on the ADNI database, and achieved 90.69% for AD/NC classification and 73.69% for p-MCI/s-MCI classification.

Original languageEnglish
Title of host publicationMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Pages212-219
Number of pages8
Volume17
Publication statusPublished - 2014

Fingerprint

Atlases
Alzheimer Disease
Learning
Brain
Databases

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Min, R., Cheng, J., Price, T., Wu, G., & Shen, D. (2014). Maximum-margin based representation learning from multiple atlases for Alzheimer's disease classification. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention (Vol. 17, pp. 212-219)

Maximum-margin based representation learning from multiple atlases for Alzheimer's disease classification. / Min, Rui; Cheng, Jian; Price, True; Wu, Guorong; Shen, Dinggang.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 17 2014. p. 212-219.

Research output: Chapter in Book/Report/Conference proceedingChapter

Min, R, Cheng, J, Price, T, Wu, G & Shen, D 2014, Maximum-margin based representation learning from multiple atlases for Alzheimer's disease classification. in Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. vol. 17, pp. 212-219.
Min R, Cheng J, Price T, Wu G, Shen D. Maximum-margin based representation learning from multiple atlases for Alzheimer's disease classification. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 17. 2014. p. 212-219
Min, Rui ; Cheng, Jian ; Price, True ; Wu, Guorong ; Shen, Dinggang. / Maximum-margin based representation learning from multiple atlases for Alzheimer's disease classification. Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 17 2014. pp. 212-219
@inbook{dcbf4bf013d4451387a3a33e5b877406,
title = "Maximum-margin based representation learning from multiple atlases for Alzheimer's disease classification",
abstract = "In order to establish the correspondences between different brains for comparison, spatial normalization based morphometric measurements have been widely used in the analysis of Alzheimer's disease (AD). In the literature, different subjects are often compared in one atlas space, which may be insufficient in revealing complex brain changes. In this paper, instead of deploying one atlas for feature extraction and classification, we propose a maximum-margin based representation learning (MMRL) method to learn the optimal representation from multiple atlases. Unlike traditional methods that perform the representation learning separately from the classification, we propose to learn the new representation jointly with the classification model, which is more powerful in discriminating AD patients from normal controls (NC). We evaluated the proposed method on the ADNI database, and achieved 90.69{\%} for AD/NC classification and 73.69{\%} for p-MCI/s-MCI classification.",
author = "Rui Min and Jian Cheng and True Price and Guorong Wu and Dinggang Shen",
year = "2014",
language = "English",
volume = "17",
pages = "212--219",
booktitle = "Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention",

}

TY - CHAP

T1 - Maximum-margin based representation learning from multiple atlases for Alzheimer's disease classification

AU - Min, Rui

AU - Cheng, Jian

AU - Price, True

AU - Wu, Guorong

AU - Shen, Dinggang

PY - 2014

Y1 - 2014

N2 - In order to establish the correspondences between different brains for comparison, spatial normalization based morphometric measurements have been widely used in the analysis of Alzheimer's disease (AD). In the literature, different subjects are often compared in one atlas space, which may be insufficient in revealing complex brain changes. In this paper, instead of deploying one atlas for feature extraction and classification, we propose a maximum-margin based representation learning (MMRL) method to learn the optimal representation from multiple atlases. Unlike traditional methods that perform the representation learning separately from the classification, we propose to learn the new representation jointly with the classification model, which is more powerful in discriminating AD patients from normal controls (NC). We evaluated the proposed method on the ADNI database, and achieved 90.69% for AD/NC classification and 73.69% for p-MCI/s-MCI classification.

AB - In order to establish the correspondences between different brains for comparison, spatial normalization based morphometric measurements have been widely used in the analysis of Alzheimer's disease (AD). In the literature, different subjects are often compared in one atlas space, which may be insufficient in revealing complex brain changes. In this paper, instead of deploying one atlas for feature extraction and classification, we propose a maximum-margin based representation learning (MMRL) method to learn the optimal representation from multiple atlases. Unlike traditional methods that perform the representation learning separately from the classification, we propose to learn the new representation jointly with the classification model, which is more powerful in discriminating AD patients from normal controls (NC). We evaluated the proposed method on the ADNI database, and achieved 90.69% for AD/NC classification and 73.69% for p-MCI/s-MCI classification.

UR - http://www.scopus.com/inward/record.url?scp=84922277193&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922277193&partnerID=8YFLogxK

M3 - Chapter

VL - 17

SP - 212

EP - 219

BT - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

ER -