Classification Trees for fast segmentation of DTI brain fiber tracts

Gali Zimmerman-Moreno*, Arnaldo Mayer, Hayit Greenspan

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

A method is proposed for modeling and classification of White Matter fiber tracts in the brain. The presented scheme uses Classification Trees in conjunction with spatial representation of the individual fibers, in order to capture the characteristic behavior of fibers belonging to a specific anatomical structure. The method is characterized by high classification speed, under 3 seconds for all the fibers in a typical DTI of a brain. The model has the ability to represent complex geometric structures and has an intuitive interpretation. Encouraging results are demonstrated for tract classification on real data from ten different subjects.

Original languageEnglish
Title of host publication2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
DOIs
StatePublished - 2008
Event2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops - Anchorage, AK, United States
Duration: 23 Jun 200828 Jun 2008

Publication series

Name2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops

Conference

Conference2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
Country/TerritoryUnited States
CityAnchorage, AK
Period23/06/0828/06/08

Fingerprint

Dive into the research topics of 'Classification Trees for fast segmentation of DTI brain fiber tracts'. Together they form a unique fingerprint.

Cite this