Welcome to the InfoSci Platform
Reference Hub6
Graph-Based Shape Analysis for MRI Classification

Graph-Based Shape Analysis for MRI Classification

Seth Long, Lawrence B. Holder
Copyright: © 2011 |Volume: 2 |Issue: 2 |Pages: 15
ISSN: 1947-9115|EISSN: 1947-9123|EISBN13: 9781613508169|DOI: 10.4018/jkdb.2011040102
Cite Article Cite Article

MLA

Long, Seth, and Lawrence B. Holder. "Graph-Based Shape Analysis for MRI Classification." IJKDB vol.2, no.2 2011: pp.19-33. http://doi.org/10.4018/jkdb.2011040102

APA

Long, S. & Holder, L. B. (2011). Graph-Based Shape Analysis for MRI Classification. International Journal of Knowledge Discovery in Bioinformatics (IJKDB), 2(2), 19-33. http://doi.org/10.4018/jkdb.2011040102

Chicago

Long, Seth, and Lawrence B. Holder. "Graph-Based Shape Analysis for MRI Classification," International Journal of Knowledge Discovery in Bioinformatics (IJKDB) 2, no.2: 19-33. http://doi.org/10.4018/jkdb.2011040102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Searching for correlations between brain structure and attributes of a person’s intellectual state is a process which may be better done by automation than by human labor. Such an automated system would be capable of performing classification based on the discovered correlation, which would be means of testing how accurate the discovered correlation is. The authors have developed a system which generates a graph-based representation of the shape of the third and lateral ventricles based on a structural MRI, and classifies images represented in this manner. The system is evaluated on accuracy at classifying individuals showing cognitive impairment to Alzheimer’s Disease. Classification accuracy is 74.2% when individuals with CDR 0.5 are included as impaired in a balanced dataset of 166 images, and 79.3% accuracy when differentiating individuals with CDR at least 1.0 and healthy individuals in a balanced dataset of 54 images. Finally, the system is used to classify MR images according to level of education, with 77.2% accuracy differentiating highly-educated individuals from those for whom no higher education is listed, in a balanced dataset of 178 images.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.