Discriminative fusion of multiple brain networks for early mild cognitive impairment detection

Qi Wang, Liang Zhan, Paul M. Thompson, Hiroko H. Dodge, Jiayu Zhou

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

6 Scopus citations

Abstract

In neuroimaging research, brain networks derived from different tractography methods may lead to different results and perform differently when used in classification tasks. As there is no ground truth to determine which brain network models are most accurate or most sensitive to group differences, we developed a new sparse learning method that combines information from multiple network models. We used it to learn a convex combination of brain connectivity matrices from 9 different tractography methods, to optimally distinguish people with early mild cognitive impairment from healthy control subjects, based on the structural connectivity patterns. Our fused networks outperformed the best single network model, Probtrackx (0.89 versus 0.77 cross-validated AUC), suggesting its potential for numerous connectivity analysis.

Original languageEnglish (US)
Title of host publication2016 IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, ISBI 2016 - Proceedings
PublisherIEEE Computer Society
Pages568-572
Number of pages5
ISBN (Electronic)9781479923502
DOIs
StatePublished - Jun 15 2016
Event2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Prague, Czech Republic
Duration: Apr 13 2016Apr 16 2016

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2016-June
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Other

Other2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016
Country/TerritoryCzech Republic
CityPrague
Period4/13/164/16/16

Keywords

  • Brain Connectome
  • Classification
  • Discriminative Fusion
  • Magnetic Resonance Imaging
  • Mild Cognitive Impairment

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Discriminative fusion of multiple brain networks for early mild cognitive impairment detection'. Together they form a unique fingerprint.

Cite this