Integrated feature extraction and selection for neuroimage classification

Yong Fan, Dinggang Shen

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

7 Citations (Scopus)

Abstract

Feature extraction and selection are of great importance in neuroimage classification for identifying informative features and reducing feature dimensionality, which are generally implemented as two separate steps. This paper presents an integrated feature extraction and selection algorithm with two iterative steps: constrained subspace learning based feature extraction and support vector machine (SVM) based feature selection. The subspace learning based feature extraction focuses on the brain regions with higher possibility of being affected by the disease under study, while the possibility of brain regions being affected by disease is estimated by the SVM based feature selection, in conjunction with SVM classification. This algorithm can not only take into account the inter-correlation among different brain regions, but also overcome the limitation of traditional subspace learning based feature extraction methods. To achieve robust performance and optimal selection of parameters involved in feature extraction, selection, and classification, a bootstrapping strategy is used to generate multiple versions of training and testing sets for parameter optimization, according to the classification performance measured by the area under the ROC (receiver operating characteristic) curve. The integrated feature extraction and selection method is applied to a structural MR image based Alzheimer's disease (AD) study with 98 non-demented and 100 demented subjects. Cross-validation results indicate that the proposed algorithm can improve performance of the traditional subspace learning based classification.

Original languageEnglish
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7259
DOIs
Publication statusPublished - 2009 Dec 15
Externally publishedYes
EventMedical Imaging 2009 - Image Processing - Lake Buena Vista, FL, United States
Duration: 2009 Feb 82009 Feb 10

Other

OtherMedical Imaging 2009 - Image Processing
CountryUnited States
CityLake Buena Vista, FL
Period09/2/809/2/10

Fingerprint

pattern recognition
Feature extraction
Learning
learning
brain
Brain
Support vector machines
ROC Curve
Alzheimer Disease
education
receivers
Support Vector Machine
optimization
curves

Keywords

  • Feature extraction
  • Feature selection
  • Neuroimage classification
  • Pattern recognition
  • Statistical methods

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Fan, Y., & Shen, D. (2009). Integrated feature extraction and selection for neuroimage classification. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 7259). [72591U] https://doi.org/10.1117/12.811781

Integrated feature extraction and selection for neuroimage classification. / Fan, Yong; Shen, Dinggang.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7259 2009. 72591U.

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

Fan, Y & Shen, D 2009, Integrated feature extraction and selection for neuroimage classification. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 7259, 72591U, Medical Imaging 2009 - Image Processing, Lake Buena Vista, FL, United States, 09/2/8. https://doi.org/10.1117/12.811781
Fan Y, Shen D. Integrated feature extraction and selection for neuroimage classification. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7259. 2009. 72591U https://doi.org/10.1117/12.811781
Fan, Yong ; Shen, Dinggang. / Integrated feature extraction and selection for neuroimage classification. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7259 2009.
@inproceedings{a47770ce52a14257872a7b47f35775ce,
title = "Integrated feature extraction and selection for neuroimage classification",
abstract = "Feature extraction and selection are of great importance in neuroimage classification for identifying informative features and reducing feature dimensionality, which are generally implemented as two separate steps. This paper presents an integrated feature extraction and selection algorithm with two iterative steps: constrained subspace learning based feature extraction and support vector machine (SVM) based feature selection. The subspace learning based feature extraction focuses on the brain regions with higher possibility of being affected by the disease under study, while the possibility of brain regions being affected by disease is estimated by the SVM based feature selection, in conjunction with SVM classification. This algorithm can not only take into account the inter-correlation among different brain regions, but also overcome the limitation of traditional subspace learning based feature extraction methods. To achieve robust performance and optimal selection of parameters involved in feature extraction, selection, and classification, a bootstrapping strategy is used to generate multiple versions of training and testing sets for parameter optimization, according to the classification performance measured by the area under the ROC (receiver operating characteristic) curve. The integrated feature extraction and selection method is applied to a structural MR image based Alzheimer's disease (AD) study with 98 non-demented and 100 demented subjects. Cross-validation results indicate that the proposed algorithm can improve performance of the traditional subspace learning based classification.",
keywords = "Feature extraction, Feature selection, Neuroimage classification, Pattern recognition, Statistical methods",
author = "Yong Fan and Dinggang Shen",
year = "2009",
month = "12",
day = "15",
doi = "10.1117/12.811781",
language = "English",
isbn = "9780819475107",
volume = "7259",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Integrated feature extraction and selection for neuroimage classification

AU - Fan, Yong

AU - Shen, Dinggang

PY - 2009/12/15

Y1 - 2009/12/15

N2 - Feature extraction and selection are of great importance in neuroimage classification for identifying informative features and reducing feature dimensionality, which are generally implemented as two separate steps. This paper presents an integrated feature extraction and selection algorithm with two iterative steps: constrained subspace learning based feature extraction and support vector machine (SVM) based feature selection. The subspace learning based feature extraction focuses on the brain regions with higher possibility of being affected by the disease under study, while the possibility of brain regions being affected by disease is estimated by the SVM based feature selection, in conjunction with SVM classification. This algorithm can not only take into account the inter-correlation among different brain regions, but also overcome the limitation of traditional subspace learning based feature extraction methods. To achieve robust performance and optimal selection of parameters involved in feature extraction, selection, and classification, a bootstrapping strategy is used to generate multiple versions of training and testing sets for parameter optimization, according to the classification performance measured by the area under the ROC (receiver operating characteristic) curve. The integrated feature extraction and selection method is applied to a structural MR image based Alzheimer's disease (AD) study with 98 non-demented and 100 demented subjects. Cross-validation results indicate that the proposed algorithm can improve performance of the traditional subspace learning based classification.

AB - Feature extraction and selection are of great importance in neuroimage classification for identifying informative features and reducing feature dimensionality, which are generally implemented as two separate steps. This paper presents an integrated feature extraction and selection algorithm with two iterative steps: constrained subspace learning based feature extraction and support vector machine (SVM) based feature selection. The subspace learning based feature extraction focuses on the brain regions with higher possibility of being affected by the disease under study, while the possibility of brain regions being affected by disease is estimated by the SVM based feature selection, in conjunction with SVM classification. This algorithm can not only take into account the inter-correlation among different brain regions, but also overcome the limitation of traditional subspace learning based feature extraction methods. To achieve robust performance and optimal selection of parameters involved in feature extraction, selection, and classification, a bootstrapping strategy is used to generate multiple versions of training and testing sets for parameter optimization, according to the classification performance measured by the area under the ROC (receiver operating characteristic) curve. The integrated feature extraction and selection method is applied to a structural MR image based Alzheimer's disease (AD) study with 98 non-demented and 100 demented subjects. Cross-validation results indicate that the proposed algorithm can improve performance of the traditional subspace learning based classification.

KW - Feature extraction

KW - Feature selection

KW - Neuroimage classification

KW - Pattern recognition

KW - Statistical methods

UR - http://www.scopus.com/inward/record.url?scp=71649112275&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71649112275&partnerID=8YFLogxK

U2 - 10.1117/12.811781

DO - 10.1117/12.811781

M3 - Conference contribution

AN - SCOPUS:71649112275

SN - 9780819475107

VL - 7259

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -