Canonical feature selection for joint regression and multi-class identification in Alzheimer’s disease diagnosis

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

Fusing information from different imaging modalities is crucial for more accurate identification of the brain state because imaging data of different modalities can provide complementary perspectives on the complex nature of brain disorders. However, most existing fusion methods often extract features independently from each modality, and then simply concatenate them into a long vector for classification, without appropriate consideration of the correlation among modalities. In this paper, we propose a novel method to transform the original features from different modalities to a common space, where the transformed features become comparable and easy to find their relation, by canonical correlation analysis. We then perform the sparse multi-task learning for discriminative feature selection by using the canonical features as regressors and penalizing a loss function with a canonical regularizer. In our experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, we use 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 multi-class disease status for Alzheimer’s disease diagnosis. The experimental results showed that the proposed canonical feature selection method helped enhance the performance of both clinical score prediction and disease status identification, outperforming the state-of-the-art methods.

Original languageEnglish
JournalBrain Imaging and Behavior
DOIs
Publication statusAccepted/In press - 2015 Aug 9

Fingerprint

Alzheimer Disease
Joints
Brain Diseases
Neuroimaging
Positron-Emission Tomography
Magnetic Resonance Imaging
Learning
Brain

Keywords

  • Alzheimer’s disease
  • Canonical correlation analysis
  • Feature selection
  • Mild cognitive impairment conversion
  • Multi-class classification

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Behavioral Neuroscience
  • Cellular and Molecular Neuroscience
  • Cognitive Neuroscience
  • Neurology
  • Psychiatry and Mental health
  • Clinical Neurology

Cite this

@article{f19561e5eb5b4c93bc1ede5c37e8fee9,
title = "Canonical feature selection for joint regression and multi-class identification in Alzheimer’s disease diagnosis",
abstract = "Fusing information from different imaging modalities is crucial for more accurate identification of the brain state because imaging data of different modalities can provide complementary perspectives on the complex nature of brain disorders. However, most existing fusion methods often extract features independently from each modality, and then simply concatenate them into a long vector for classification, without appropriate consideration of the correlation among modalities. In this paper, we propose a novel method to transform the original features from different modalities to a common space, where the transformed features become comparable and easy to find their relation, by canonical correlation analysis. We then perform the sparse multi-task learning for discriminative feature selection by using the canonical features as regressors and penalizing a loss function with a canonical regularizer. In our experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, we use 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 multi-class disease status for Alzheimer’s disease diagnosis. The experimental results showed that the proposed canonical feature selection method helped enhance the performance of both clinical score prediction and disease status identification, outperforming the state-of-the-art methods.",
keywords = "Alzheimer’s disease, Canonical correlation analysis, Feature selection, Mild cognitive impairment conversion, Multi-class classification",
author = "Xiaofeng Zhu and Heung-Il Suk and Lee, {Seong Whan} and Dinggang Shen",
year = "2015",
month = "8",
day = "9",
doi = "10.1007/s11682-015-9430-4",
language = "English",
journal = "Brain Imaging and Behavior",
issn = "1931-7557",
publisher = "Springer New York",

}

TY - JOUR

T1 - Canonical feature selection for joint regression and multi-class identification in Alzheimer’s disease diagnosis

AU - Zhu, Xiaofeng

AU - Suk, Heung-Il

AU - Lee, Seong Whan

AU - Shen, Dinggang

PY - 2015/8/9

Y1 - 2015/8/9

N2 - Fusing information from different imaging modalities is crucial for more accurate identification of the brain state because imaging data of different modalities can provide complementary perspectives on the complex nature of brain disorders. However, most existing fusion methods often extract features independently from each modality, and then simply concatenate them into a long vector for classification, without appropriate consideration of the correlation among modalities. In this paper, we propose a novel method to transform the original features from different modalities to a common space, where the transformed features become comparable and easy to find their relation, by canonical correlation analysis. We then perform the sparse multi-task learning for discriminative feature selection by using the canonical features as regressors and penalizing a loss function with a canonical regularizer. In our experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, we use 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 multi-class disease status for Alzheimer’s disease diagnosis. The experimental results showed that the proposed canonical feature selection method helped enhance the performance of both clinical score prediction and disease status identification, outperforming the state-of-the-art methods.

AB - Fusing information from different imaging modalities is crucial for more accurate identification of the brain state because imaging data of different modalities can provide complementary perspectives on the complex nature of brain disorders. However, most existing fusion methods often extract features independently from each modality, and then simply concatenate them into a long vector for classification, without appropriate consideration of the correlation among modalities. In this paper, we propose a novel method to transform the original features from different modalities to a common space, where the transformed features become comparable and easy to find their relation, by canonical correlation analysis. We then perform the sparse multi-task learning for discriminative feature selection by using the canonical features as regressors and penalizing a loss function with a canonical regularizer. In our experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, we use 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 multi-class disease status for Alzheimer’s disease diagnosis. The experimental results showed that the proposed canonical feature selection method helped enhance the performance of both clinical score prediction and disease status identification, outperforming the state-of-the-art methods.

KW - Alzheimer’s disease

KW - Canonical correlation analysis

KW - Feature selection

KW - Mild cognitive impairment conversion

KW - Multi-class classification

UR - http://www.scopus.com/inward/record.url?scp=84938780497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938780497&partnerID=8YFLogxK

U2 - 10.1007/s11682-015-9430-4

DO - 10.1007/s11682-015-9430-4

M3 - Article

C2 - 26254746

AN - SCOPUS:84938780497

JO - Brain Imaging and Behavior

JF - Brain Imaging and Behavior

SN - 1931-7557

ER -