Skip to main content
placeholder image

Exploring compact representation of SICE matrices for functional brain network classification

Chapter


Abstract


  • Recently, sparse inverse covariance matrix (SICE matrix) has been used as a representation of brain connectivity to classify Alzheimer’s disease and normal controls. However, its high dimensionality can adversely affect the classification performance. Considering the underlying manifold where SICE matrices reside and the common patterns shared by brain connectivity across subjects, we propose to explore the lower dimensional intrinsic components of SICE matrix for compact representation. This leads to significant improvements of brain connectivity classification. Moreover, to cater for the requirement of both discrimination and interpretation in neuroimage analysis, we develop a novel pre-image estimation algorithm to make the obtained connectivity components anatomically interpretable. The advantages of our method have been well demonstrated on both synthetic and real rs-fMRI data sets.

Publication Date


  • 2014

Citation


  • Zhang, J., Zhou, L., Wang, L. & Li, W. (2014). Exploring compact representation of SICE matrices for functional brain network classification. In G. Wu, D. Zhang & L. Zhou (Eds.), Machine Learning in Medical Imaging 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings (pp. 59-67). Switzerland: Springer International Publishing.

International Standard Book Number (isbn) 13


  • 9783319105802

Scopus Eid


  • 2-s2.0-84921643210

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/4136

Book Title


  • Machine Learning in Medical Imaging 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings

Has Global Citation Frequency


Start Page


  • 59

End Page


  • 67

Place Of Publication


  • Switzerland

Abstract


  • Recently, sparse inverse covariance matrix (SICE matrix) has been used as a representation of brain connectivity to classify Alzheimer’s disease and normal controls. However, its high dimensionality can adversely affect the classification performance. Considering the underlying manifold where SICE matrices reside and the common patterns shared by brain connectivity across subjects, we propose to explore the lower dimensional intrinsic components of SICE matrix for compact representation. This leads to significant improvements of brain connectivity classification. Moreover, to cater for the requirement of both discrimination and interpretation in neuroimage analysis, we develop a novel pre-image estimation algorithm to make the obtained connectivity components anatomically interpretable. The advantages of our method have been well demonstrated on both synthetic and real rs-fMRI data sets.

Publication Date


  • 2014

Citation


  • Zhang, J., Zhou, L., Wang, L. & Li, W. (2014). Exploring compact representation of SICE matrices for functional brain network classification. In G. Wu, D. Zhang & L. Zhou (Eds.), Machine Learning in Medical Imaging 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings (pp. 59-67). Switzerland: Springer International Publishing.

International Standard Book Number (isbn) 13


  • 9783319105802

Scopus Eid


  • 2-s2.0-84921643210

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/4136

Book Title


  • Machine Learning in Medical Imaging 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings

Has Global Citation Frequency


Start Page


  • 59

End Page


  • 67

Place Of Publication


  • Switzerland