Share Email Print

Journal of Medical Imaging

Etiology-based classification of brain white matter hyperintensity on magnetic resonance imaging
Author(s): Mariana Leite; Leticia Rittner; Simone Appenzeller; Heloísa Helena Ruocco; Roberto A. Lotufo
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Brain white matter lesions found upon magnetic resonance imaging are often observed in psychiatric or neurological patients. Individuals with these lesions present a more significant cognitive impairment when compared with individuals without them. We propose a computerized method to distinguish tissue containing white matter lesions of different etiologies (e.g., demyelinating or ischemic) using texture-based classifiers. Texture attributes were extracted from manually selected regions of interest and used to train and test supervised classifiers. Experiments were conducted to evaluate texture attribute discrimination and classifiers’ performances. The most discriminating texture attributes were obtained from the gray-level histogram and from the co-occurrence matrix. The best classifier was the support vector machine, which achieved an accuracy of 87.9% in distinguishing lesions with different etiologies and an accuracy of 99.29% in distinguishing normal white matter from white matter lesions.

Paper Details

Date Published: 19 February 2015
PDF: 10 pages
J. Med. Imag. 2(1) 014002 doi: 10.1117/1.JMI.2.1.014002
Published in: Journal of Medical Imaging Volume 2, Issue 1
Show Author Affiliations
Mariana Leite, Univ. Estadual de Campinas (Brazil)
Leticia Rittner, Univ. Estadual de Campinas (Brazil)
Simone Appenzeller, Univ. Estadual de Campinas (Brazil)
Heloísa Helena Ruocco, Faculdade de Medicina de Jundiai (Brazil)
Roberto A. Lotufo, Univ. Estadual de Campinas (Brazil)

© SPIE. Terms of Use
Back to Top