Discriminative Multi-task Feature Selection for Multi-modality Based AD/MCI Classification

Tingting Ye, Chen Zu, Biao Jie, Dinggang Shen, Daoqiang Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Recently, multi-task based feature selection methods have been used in multi-modality based classification of Alzheimer's disease (AD) and its prodromal stage, i.e., Mild cognitive impairment (MCI). However, in traditional multi-task feature selection methods, some useful discriminative information among subjects is usually not well mined for further improving the subsequent classification performance. Accordingly, in this paper, we propose a discriminative multi-task feature selection method to select the most discriminative features for multi-modality based classification of AD/MCI. Specifically, for each modality, we traina linear regression model using the corresponding modality of data, and further enforce the group-sparsity regularization on weights of those regression models for joint selection of common features across multiple modalities. Furthermore, we propose a discriminative regularization term based on the intra-class and inter-class Laplacian matrices to better use the discriminative information among subjects. We perform extensive experiments on 202 subjects from the baseline MRI and FDG-PET image data of the Alzheimer's Disease Neuroimaging Initiative (ADNI). The experimental results show that our proposed method improves the classification performance with the comparison to several state-of the-art methods for multi-modality based AD/MCI classification.

Original languageEnglish
Title of host publicationProceedings - 2015 International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages45-48
Number of pages4
ISBN (Print)9781467371452
DOIs
Publication statusPublished - 2015 Sep 16
Externally publishedYes
Event5th International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015 - Stanford, United States
Duration: 2015 Jun 102015 Jun 12

Other

Other5th International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015
CountryUnited States
CityStanford
Period15/6/1015/6/12

Fingerprint

Feature extraction
Alzheimer Disease
Linear Models
Neuroimaging
Prodromal Symptoms
Linear regression
Magnetic resonance imaging
Cognitive Dysfunction
Weights and Measures
Experiments

Keywords

  • Alzheimer's disease
  • discriminative regularization
  • group-sparsity regularizer
  • multi-modality based classification
  • multi-task feature selection

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Radiology Nuclear Medicine and imaging

Cite this

Ye, T., Zu, C., Jie, B., Shen, D., & Zhang, D. (2015). Discriminative Multi-task Feature Selection for Multi-modality Based AD/MCI Classification. In Proceedings - 2015 International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015 (pp. 45-48). [7270844] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PRNI.2015.15

Discriminative Multi-task Feature Selection for Multi-modality Based AD/MCI Classification. / Ye, Tingting; Zu, Chen; Jie, Biao; Shen, Dinggang; Zhang, Daoqiang.

Proceedings - 2015 International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 45-48 7270844.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ye, T, Zu, C, Jie, B, Shen, D & Zhang, D 2015, Discriminative Multi-task Feature Selection for Multi-modality Based AD/MCI Classification. in Proceedings - 2015 International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015., 7270844, Institute of Electrical and Electronics Engineers Inc., pp. 45-48, 5th International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015, Stanford, United States, 15/6/10. https://doi.org/10.1109/PRNI.2015.15
Ye T, Zu C, Jie B, Shen D, Zhang D. Discriminative Multi-task Feature Selection for Multi-modality Based AD/MCI Classification. In Proceedings - 2015 International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 45-48. 7270844 https://doi.org/10.1109/PRNI.2015.15
Ye, Tingting ; Zu, Chen ; Jie, Biao ; Shen, Dinggang ; Zhang, Daoqiang. / Discriminative Multi-task Feature Selection for Multi-modality Based AD/MCI Classification. Proceedings - 2015 International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 45-48
@inproceedings{1fafc039752d4b659e1ad06d22662962,
title = "Discriminative Multi-task Feature Selection for Multi-modality Based AD/MCI Classification",
abstract = "Recently, multi-task based feature selection methods have been used in multi-modality based classification of Alzheimer's disease (AD) and its prodromal stage, i.e., Mild cognitive impairment (MCI). However, in traditional multi-task feature selection methods, some useful discriminative information among subjects is usually not well mined for further improving the subsequent classification performance. Accordingly, in this paper, we propose a discriminative multi-task feature selection method to select the most discriminative features for multi-modality based classification of AD/MCI. Specifically, for each modality, we traina linear regression model using the corresponding modality of data, and further enforce the group-sparsity regularization on weights of those regression models for joint selection of common features across multiple modalities. Furthermore, we propose a discriminative regularization term based on the intra-class and inter-class Laplacian matrices to better use the discriminative information among subjects. We perform extensive experiments on 202 subjects from the baseline MRI and FDG-PET image data of the Alzheimer's Disease Neuroimaging Initiative (ADNI). The experimental results show that our proposed method improves the classification performance with the comparison to several state-of the-art methods for multi-modality based AD/MCI classification.",
keywords = "Alzheimer's disease, discriminative regularization, group-sparsity regularizer, multi-modality based classification, multi-task feature selection",
author = "Tingting Ye and Chen Zu and Biao Jie and Dinggang Shen and Daoqiang Zhang",
year = "2015",
month = "9",
day = "16",
doi = "10.1109/PRNI.2015.15",
language = "English",
isbn = "9781467371452",
pages = "45--48",
booktitle = "Proceedings - 2015 International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Discriminative Multi-task Feature Selection for Multi-modality Based AD/MCI Classification

AU - Ye, Tingting

AU - Zu, Chen

AU - Jie, Biao

AU - Shen, Dinggang

AU - Zhang, Daoqiang

PY - 2015/9/16

Y1 - 2015/9/16

N2 - Recently, multi-task based feature selection methods have been used in multi-modality based classification of Alzheimer's disease (AD) and its prodromal stage, i.e., Mild cognitive impairment (MCI). However, in traditional multi-task feature selection methods, some useful discriminative information among subjects is usually not well mined for further improving the subsequent classification performance. Accordingly, in this paper, we propose a discriminative multi-task feature selection method to select the most discriminative features for multi-modality based classification of AD/MCI. Specifically, for each modality, we traina linear regression model using the corresponding modality of data, and further enforce the group-sparsity regularization on weights of those regression models for joint selection of common features across multiple modalities. Furthermore, we propose a discriminative regularization term based on the intra-class and inter-class Laplacian matrices to better use the discriminative information among subjects. We perform extensive experiments on 202 subjects from the baseline MRI and FDG-PET image data of the Alzheimer's Disease Neuroimaging Initiative (ADNI). The experimental results show that our proposed method improves the classification performance with the comparison to several state-of the-art methods for multi-modality based AD/MCI classification.

AB - Recently, multi-task based feature selection methods have been used in multi-modality based classification of Alzheimer's disease (AD) and its prodromal stage, i.e., Mild cognitive impairment (MCI). However, in traditional multi-task feature selection methods, some useful discriminative information among subjects is usually not well mined for further improving the subsequent classification performance. Accordingly, in this paper, we propose a discriminative multi-task feature selection method to select the most discriminative features for multi-modality based classification of AD/MCI. Specifically, for each modality, we traina linear regression model using the corresponding modality of data, and further enforce the group-sparsity regularization on weights of those regression models for joint selection of common features across multiple modalities. Furthermore, we propose a discriminative regularization term based on the intra-class and inter-class Laplacian matrices to better use the discriminative information among subjects. We perform extensive experiments on 202 subjects from the baseline MRI and FDG-PET image data of the Alzheimer's Disease Neuroimaging Initiative (ADNI). The experimental results show that our proposed method improves the classification performance with the comparison to several state-of the-art methods for multi-modality based AD/MCI classification.

KW - Alzheimer's disease

KW - discriminative regularization

KW - group-sparsity regularizer

KW - multi-modality based classification

KW - multi-task feature selection

UR - http://www.scopus.com/inward/record.url?scp=84961825641&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961825641&partnerID=8YFLogxK

U2 - 10.1109/PRNI.2015.15

DO - 10.1109/PRNI.2015.15

M3 - Conference contribution

AN - SCOPUS:84961825641

SN - 9781467371452

SP - 45

EP - 48

BT - Proceedings - 2015 International Workshop on Pattern Recognition in NeuroImaging, PRNI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -