Multi-modality canonical feature selection for Alzheimer's disease diagnosis

Research output: Chapter in Book/Report/Conference proceedingChapter

19 Citations (Scopus)

Abstract

Feature selection has been commonly regarded as an effective method to lessen the problem of high dimension and low sample size in medical image analysis. In this paper, we propose a novel multimodality canonical feature selection method. Unlike the conventional sparse Multi-Task Learning (MTL) based feature selection method that mostly considered only the relationship between target response variables, we further consider the correlations between features of different modalities by projecting them into a canonical space determined by canonical correlation analysis. We call the projections as canonical representations. By setting the canonical representations as regressors in a sparse least square regression framework and by further penalizing the objective function with a new canonical regularizer on the weight coefficient matrix, we formulate a multi-modality canonical feature selection method. With the help of the canonical information of canonical representations and also a canonical regularizer, the proposed method selects canonical-cross-modality features that are useful for the tasks of clinical scores regression and multi-class disease identification. In our experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, we combine Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) images to jointly predict clinical scores of Alzheimer's Disease Assessment Scale-Cognitive subscale (ADAS-Cog) and Mini-Mental State Examination (MMSE) and also identify multiclass disease status for Alzheimer's disease diagnosis.

Original languageEnglish
Title of host publicationMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Pages162-169
Number of pages8
Volume17
Publication statusPublished - 2014 Jan 1

Fingerprint

Alzheimer Disease
Least-Squares Analysis
Neuroimaging
Positron-Emission Tomography
Sample Size
Magnetic Resonance Imaging
Learning
Weights and Measures

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Zhu, X., Suk, H-I., & Shen, D. (2014). Multi-modality canonical feature selection for Alzheimer's disease diagnosis. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention (Vol. 17, pp. 162-169)

Multi-modality canonical feature selection for Alzheimer's disease diagnosis. / Zhu, Xiaofeng; Suk, Heung-Il; Shen, Dinggang.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 17 2014. p. 162-169.

Research output: Chapter in Book/Report/Conference proceedingChapter

Zhu, X, Suk, H-I & Shen, D 2014, Multi-modality canonical feature selection for Alzheimer's disease diagnosis. in Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. vol. 17, pp. 162-169.
Zhu X, Suk H-I, Shen D. Multi-modality canonical feature selection for Alzheimer's disease diagnosis. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 17. 2014. p. 162-169
Zhu, Xiaofeng ; Suk, Heung-Il ; Shen, Dinggang. / Multi-modality canonical feature selection for Alzheimer's disease diagnosis. Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 17 2014. pp. 162-169
@inbook{d46268c2fdfd4635a3bbb4ec6c1d0be7,
title = "Multi-modality canonical feature selection for Alzheimer's disease diagnosis",
abstract = "Feature selection has been commonly regarded as an effective method to lessen the problem of high dimension and low sample size in medical image analysis. In this paper, we propose a novel multimodality canonical feature selection method. Unlike the conventional sparse Multi-Task Learning (MTL) based feature selection method that mostly considered only the relationship between target response variables, we further consider the correlations between features of different modalities by projecting them into a canonical space determined by canonical correlation analysis. We call the projections as canonical representations. By setting the canonical representations as regressors in a sparse least square regression framework and by further penalizing the objective function with a new canonical regularizer on the weight coefficient matrix, we formulate a multi-modality canonical feature selection method. With the help of the canonical information of canonical representations and also a canonical regularizer, the proposed method selects canonical-cross-modality features that are useful for the tasks of clinical scores regression and multi-class disease identification. In our experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, we combine Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) images to jointly predict clinical scores of Alzheimer's Disease Assessment Scale-Cognitive subscale (ADAS-Cog) and Mini-Mental State Examination (MMSE) and also identify multiclass disease status for Alzheimer's disease diagnosis.",
author = "Xiaofeng Zhu and Heung-Il Suk and Dinggang Shen",
year = "2014",
month = "1",
day = "1",
language = "English",
volume = "17",
pages = "162--169",
booktitle = "Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention",

}

TY - CHAP

T1 - Multi-modality canonical feature selection for Alzheimer's disease diagnosis

AU - Zhu, Xiaofeng

AU - Suk, Heung-Il

AU - Shen, Dinggang

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Feature selection has been commonly regarded as an effective method to lessen the problem of high dimension and low sample size in medical image analysis. In this paper, we propose a novel multimodality canonical feature selection method. Unlike the conventional sparse Multi-Task Learning (MTL) based feature selection method that mostly considered only the relationship between target response variables, we further consider the correlations between features of different modalities by projecting them into a canonical space determined by canonical correlation analysis. We call the projections as canonical representations. By setting the canonical representations as regressors in a sparse least square regression framework and by further penalizing the objective function with a new canonical regularizer on the weight coefficient matrix, we formulate a multi-modality canonical feature selection method. With the help of the canonical information of canonical representations and also a canonical regularizer, the proposed method selects canonical-cross-modality features that are useful for the tasks of clinical scores regression and multi-class disease identification. In our experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, we combine Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) images to jointly predict clinical scores of Alzheimer's Disease Assessment Scale-Cognitive subscale (ADAS-Cog) and Mini-Mental State Examination (MMSE) and also identify multiclass disease status for Alzheimer's disease diagnosis.

AB - Feature selection has been commonly regarded as an effective method to lessen the problem of high dimension and low sample size in medical image analysis. In this paper, we propose a novel multimodality canonical feature selection method. Unlike the conventional sparse Multi-Task Learning (MTL) based feature selection method that mostly considered only the relationship between target response variables, we further consider the correlations between features of different modalities by projecting them into a canonical space determined by canonical correlation analysis. We call the projections as canonical representations. By setting the canonical representations as regressors in a sparse least square regression framework and by further penalizing the objective function with a new canonical regularizer on the weight coefficient matrix, we formulate a multi-modality canonical feature selection method. With the help of the canonical information of canonical representations and also a canonical regularizer, the proposed method selects canonical-cross-modality features that are useful for the tasks of clinical scores regression and multi-class disease identification. In our experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, we combine Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) images to jointly predict clinical scores of Alzheimer's Disease Assessment Scale-Cognitive subscale (ADAS-Cog) and Mini-Mental State Examination (MMSE) and also identify multiclass disease status for Alzheimer's disease diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=84922326849&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922326849&partnerID=8YFLogxK

M3 - Chapter

VL - 17

SP - 162

EP - 169

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

ER -