Homogeneity-based Feature Extraction for Classification of Early-stage Alzheimer’s disease from Functional Magnetic Resonance Images
published: Oct. 4, 2011, recorded: August 2011, views: 3789
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Alzheimer's disease is the most common form of age-related dementia. Early-stage diagnosis of Alzheimer is of major importance for the following reasons: Also easily curable conditions like depression, poor nutrition and drug side effects may cause symptoms like early-stage Alzheimer. Moreover, recently some medications have been developed which successfully attenuate the symptoms and delay the progression of Alzheimer, but to be effective, they need to be applied as soon as possible. However, early-stage diagnosis of Alzheimer is very difficult since the symptoms are very mild and can easily be confounded with effects of normal aging. In this paper, we introduce a bootstrapping-based feature extraction technique to identify early-stage Alzheimer's disease from resting-state functional resonance images. Our experiments demonstrate that subjects with early-stage Alzheimer's disease can be distinguished with an accuracy of 79% from age-matched healthy subjects using a support vector machine on the extracted features.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !