By Topic

Parallel nonlinear analysis of weighted brain's gray and white matter images for Alzheimer's dementia diagnosis

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Seiied-Mohammad-Javad Razavian ; Computer Science Department of Sharif University of Technology, Tehran, Iran ; Meysam Torabi ; Kio Kim

In this study, we are proposing a novel nonlinear classification approach to discriminate between Alzheimer's Disease (AD) and a control group using T1-weighted and T2-weighted Magnetic Resonance Images (MRI's) of brain. Since T1-weighted images and T2-weighted images have inherent physical differences, obviously each of them has its own particular medical data and hence, we extracted some specific features from each. Then the variations of the relevant eigenvalues of the extracted features were tracked to pick up the most informative ones. The final features were assigned to two parallel systems to be nonlinearly categorized. Considering the fact that AD defects the white and gray regions of brain more than its black and marginal regions, and also since T1-weighted has more medical data of white and gray regions than T2-weighted images, we put optimal weights for the two outputs. Combination of these two results made the final decision of AD diagnosis system. The dataset includes 60 T1-weighted images and 60 T2-weighted images of normal and abnormal cases. The dataset which includes different cross-sections of the brain, after an accurate registration, was split to two groups of test set (40 percent of the dataset) and training set (60 percent of the dataset). The results demonstrate more than two thirds of accuracy in detection of normal and abnormal images.

Published in:

2010 Annual International Conference of the IEEE Engineering in Medicine and Biology

Date of Conference:

Aug. 31 2010-Sept. 4 2010