Statistical feature selection and classification models for Alzheimer's disease progression assessment

• Published in: 2016 IEEE Nuclear Science Symposium, Medical Imaging Conference and Room-Temperature Semiconductor Detector Workshop (NSS/MIC/RTSD) pp. 1 - 5
• Main Authors: Dominguez, A., Ramirez, J., Gorriz, J. M., Segovia, F., Salas-Gonzalez, D., Martinez-Murcia, F. J., Illan, I. A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2016
• Subjects: Dementia; Feature extraction; Image segmentation; Principal component analysis; Support vector machines
• DOI: 10.1109/NSSMIC.2016.8069560

Alzheimer's disease (AD) is a progressive course neurodegenerative disease and the most common cause of dementia. Prediction of its progression from mild-cognitive impairment (MCI) to AD is still a challenging problem. This paper shows a system using tissue-segmented T1 magnetic resonance imaging (MRI) and neuropsychological tests including Mini Mental State Examination (MMSE) and cognitive assessment subscale (ADAS-Cog) to predict whether an MCI patient will evolve to AD within six months. Three alternative MRI feature extraction methods are considered: i) computation of brain region statistics by means of a regional atlas defining 116 regions of interest (ROIs), ii) voxel-based principal component analysis (PCA), and iii) voxel-based partial least squares (PLS). A t-test feature selection method is used to identify the most discriminant features for MCI to AD prediction that serve as input to a support vector machine (SVM) classifier that groups MCI subjects remaining stable during six months from those who progress to AD.