PROJECT TITLE :

Extracting Salient Brain Patterns For Imaging Based Classification Of Neurodegenerative Diseases - 2014

ABSTRACT:

Neurodegenerative diseases comprise a wide range of mental symptoms whose evolution is not directly related to the visual analysis created by radiologists, who will hardly quantify systematic variations. Moreover, automatic brain morphometric analyses, that do perform this quantification, contribute very very little to the comprehension of the disease, i.e., several of these ways classify but they do not produce helpful anatomo-practical correlations. This paper presents a new absolutely automatic image analysis technique that reveals discriminative brain patterns associated to the presence of neurodegenerative diseases, mining systematic differences and so grading objectively any neurological disorder. This can be accomplished by a fusion strategy that mixes together bottom-up and high-down information flows. Bottom-up data comes from a multiscale analysis of various image options, while the top-down stage includes learning and fusion strategies formulated as a max-margin multiple-kernel optimization drawback. The capability of finding discriminative anatomic patterns was evaluated using the Alzheimer's disease (AD) as the use case. The classification performance was assessed beneath different configurations of the proposed approach in two public brain magnetic resonance datasets (OASIS-MIRIAD) with patients diagnosed with AD, showing an improvement varying from six.two% to 13% in the equal error rate measure, with respect to what has been reported by the feature-based morphometry strategy. In terms of the anatomical analysis, discriminant regions found by the proposed approach highly correlates to what has been reported in clinical studies of AD.