Spatial Component Analysis of MRI data for Alzheimer's Disease Diagnosis: a Bayesian network approach

• Main Authors: Ignacio eA. Illán, Juan Manuel Gorriz, Javier eRamírez, Anke eMeyer-Baese
• Format: Article
• Language: English
• Published: Frontiers Media S.A. 2014-11-01
• Series: Frontiers in Computational Neuroscience
• Subjects: Magnetic Resonance Imaging; bayesian networks; AD diagnosis; Spatial Component Analysis; CAD systems
• Online Access: http://journal.frontiersin.org/Journal/10.3389/fncom.2014.00156/full
• ISSN: 1662-5188

This work presents a spatial-component (SC) based approach to aid the diagnosis of Alzheimer's disease (AD) using magnetic resonance images. In this approach, the whole brain image is subdivided in regions or spatial components, and a Bayesian network is used to model the dependencies between affected regions of AD. The structure of relations between affected regions allows to detect neurodegeneration with an estimated performance of 88 % on more than 400 subjects and predict neurodegeneration with 80 % accuracy, supporting the conclusion that modelling the dependencies between components increases the recognition of different patterns of brain degeneration in AD.