Detecting cognitive states from fMRI images by machine learning and multivariate classification

Yong Fan, Dinggang Shen, Christos Davatzikos

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

27 Citations (Scopus)

Abstract

The major obstacle in building classifiers that robustly detect a particular cognitive state across different subjects using fMRI images has been the high inter-subject functional variability in brain activation patterns. To overcome this obstacle, firstly, the brain regions that are relevant to the problem under study are determined from the training data; then, statistical information of each brain region is extracted to form regional features, which are robust to inter-subject functional variations within the brain region; finally, the regional feature statistical variations across different samples are further alleviated by a PCA technique. To improve the generalization ability and efficiency of the classification, from the extracted regional features, a hybrid feature selection method is utilized to select the most discriminative features, which are used to train a SVM classifier for decoding brain states from fMRI images. The performance of this method is validated in a deception fMRI study. The proposed method yielded better results compared to other commonly used fMRI image classification methods.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2006
DOIs
Publication statusPublished - 2006 Dec 21
Externally publishedYes
Event2006 Conference on Computer Vision and Pattern Recognition Workshops - New York, NY, United States
Duration: 2006 Jun 172006 Jun 22

Other

Other2006 Conference on Computer Vision and Pattern Recognition Workshops
CountryUnited States
CityNew York, NY
Period06/6/1706/6/22

Fingerprint

Learning systems
Brain
Classifiers
Image classification
Decoding
Feature extraction
Chemical activation
Magnetic Resonance Imaging

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Fan, Y., Shen, D., & Davatzikos, C. (2006). Detecting cognitive states from fMRI images by machine learning and multivariate classification. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 2006). [1640530] https://doi.org/10.1109/CVPRW.2006.64

Detecting cognitive states from fMRI images by machine learning and multivariate classification. / Fan, Yong; Shen, Dinggang; Davatzikos, Christos.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 2006 2006. 1640530.

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

Fan, Y, Shen, D & Davatzikos, C 2006, Detecting cognitive states from fMRI images by machine learning and multivariate classification. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. vol. 2006, 1640530, 2006 Conference on Computer Vision and Pattern Recognition Workshops, New York, NY, United States, 06/6/17. https://doi.org/10.1109/CVPRW.2006.64
Fan Y, Shen D, Davatzikos C. Detecting cognitive states from fMRI images by machine learning and multivariate classification. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 2006. 2006. 1640530 https://doi.org/10.1109/CVPRW.2006.64
Fan, Yong ; Shen, Dinggang ; Davatzikos, Christos. / Detecting cognitive states from fMRI images by machine learning and multivariate classification. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 2006 2006.
@inproceedings{6b6d27c392d64d15ac9a97970bd70b6f,
title = "Detecting cognitive states from fMRI images by machine learning and multivariate classification",
abstract = "The major obstacle in building classifiers that robustly detect a particular cognitive state across different subjects using fMRI images has been the high inter-subject functional variability in brain activation patterns. To overcome this obstacle, firstly, the brain regions that are relevant to the problem under study are determined from the training data; then, statistical information of each brain region is extracted to form regional features, which are robust to inter-subject functional variations within the brain region; finally, the regional feature statistical variations across different samples are further alleviated by a PCA technique. To improve the generalization ability and efficiency of the classification, from the extracted regional features, a hybrid feature selection method is utilized to select the most discriminative features, which are used to train a SVM classifier for decoding brain states from fMRI images. The performance of this method is validated in a deception fMRI study. The proposed method yielded better results compared to other commonly used fMRI image classification methods.",
author = "Yong Fan and Dinggang Shen and Christos Davatzikos",
year = "2006",
month = "12",
day = "21",
doi = "10.1109/CVPRW.2006.64",
language = "English",
isbn = "0769526462",
volume = "2006",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Detecting cognitive states from fMRI images by machine learning and multivariate classification

AU - Fan, Yong

AU - Shen, Dinggang

AU - Davatzikos, Christos

PY - 2006/12/21

Y1 - 2006/12/21

N2 - The major obstacle in building classifiers that robustly detect a particular cognitive state across different subjects using fMRI images has been the high inter-subject functional variability in brain activation patterns. To overcome this obstacle, firstly, the brain regions that are relevant to the problem under study are determined from the training data; then, statistical information of each brain region is extracted to form regional features, which are robust to inter-subject functional variations within the brain region; finally, the regional feature statistical variations across different samples are further alleviated by a PCA technique. To improve the generalization ability and efficiency of the classification, from the extracted regional features, a hybrid feature selection method is utilized to select the most discriminative features, which are used to train a SVM classifier for decoding brain states from fMRI images. The performance of this method is validated in a deception fMRI study. The proposed method yielded better results compared to other commonly used fMRI image classification methods.

AB - The major obstacle in building classifiers that robustly detect a particular cognitive state across different subjects using fMRI images has been the high inter-subject functional variability in brain activation patterns. To overcome this obstacle, firstly, the brain regions that are relevant to the problem under study are determined from the training data; then, statistical information of each brain region is extracted to form regional features, which are robust to inter-subject functional variations within the brain region; finally, the regional feature statistical variations across different samples are further alleviated by a PCA technique. To improve the generalization ability and efficiency of the classification, from the extracted regional features, a hybrid feature selection method is utilized to select the most discriminative features, which are used to train a SVM classifier for decoding brain states from fMRI images. The performance of this method is validated in a deception fMRI study. The proposed method yielded better results compared to other commonly used fMRI image classification methods.

UR - http://www.scopus.com/inward/record.url?scp=33845538512&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845538512&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2006.64

DO - 10.1109/CVPRW.2006.64

M3 - Conference contribution

SN - 0769526462

SN - 9780769526461

VL - 2006

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -