Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Max-margin based learning for discriminative Bayesian network from neuroimaging data
Author: Zhou, L.
Wang, L.
Liu, L.
Ogunbona, P.
Shen, D.
Citation: Proceedings of the 17th International Conference on Medical Image Computing and Computer-Assisted Intervention, 2014 / vol.8675 LNCS, iss.Part III, pp.321-328
Publisher: Springer
Issue Date: 2014
Series/Report no.: Lecture Notes in Computer Science (LNCS, vol. 8675)
ISBN: 9783319104423
ISSN: 0302-9743
Conference Name: 17th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2014) (14 Sep 2014 - 18 Sep 2014 : Boston, MA, USA)
Statement of
Luping Zhou, Lei Wang, Lingqiao Liu, Philip Ogunbona, and Dinggang Shen
Abstract: Recently, neuroimaging data have been increasingly used to study the causal relationship among brain regions for the understanding and diagnosis of brain diseases. Recent work on sparse Gaussian Bayesian network (SGBN) has shown it as an efficient tool to learn large scale directional brain networks from neuroimaging data. In this paper, we propose a learning approach to constructing SGBNs that are both representative and discriminative for groups in comparison. A maxmargin criterion built directly upon the SGBN models is proposed to effectively optimize the classification performance of the SGBNs. The proposed method shows significant improvements over the state-of-theart works in the discriminative power of SGBNs.
Keywords: Nerve Net; Humans; Alzheimer Disease; Image Interpretation, Computer-Assisted; Discriminant Analysis; Bayes Theorem; Sensitivity and Specificity; Reproducibility of Results; Artificial Intelligence; Pattern Recognition, Automated; Neuroimaging; Connectome
Rights: © Springer International Publishing Switzerland 2014
RMID: 0030028883
DOI: 10.1007/978-3-319-10443-0_41
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_109070.pdfRestricted Access348.95 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.