Title	A METHOD FOR CLUSTERING BRAIN FIBERS.
Author	Prasad, Shilpa
Advisors	Gangopadhyay, Dr. Aryya
Program	Information Systems
UMBC Department	Information Systems
Document Type	thesis
Sponsors	University of Maryland, Baltimore County (UMBC).
Keywords	Brain Fibers; Classification; Clustering; Data Mining; Principal Component Analysis; Statistical Analysis
Date Issued	2010-01-01
Abstract	The human brain has over 150,000 km of fibers connecting hundreds of billions of neurons. The axons travel in identifiable fiber tracts and following a similar path as a bundle of fibers pass through the brain. These tracts appear in atlases and are used by surgeons and neuroscientists. Although, organization of brain fibers and its white matter is complex and not completely elucidated it is important to understand the organization of the brain. It helps in dealing with brain tumors, intra ventricular lesions, intra cerebral hematomas and others. The goal of this thesis is to take the set of 250,000 stream lines of brain axon paths and cluster them into 20-50 fiber tracts that provide a consistent segmentation across multiple scans. We have used two methods to cluster brain. In first method, we have used classification and clustering algorithms. In second method we have used clustering and distance based measure.
Identifier	10387
Format	application:pdf
Language	en
Collection	UMBC Thesis and Dissertations.
Rights Statement	This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. for permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu.
Source	Prasad_umbc_0434M_10387.pdf
Access Rights	Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan through a local library, pending author/copyright holder's permission.

A METHOD FOR CLUSTERING BRAIN FIBERS.

Description

Tags

Comments