Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects

• Published in: NeuroImage (Orlando, Fla.) Vol. 104; pp. 398 - 412
• Main Authors: Moradi, Elaheh, Pepe, Antonietta, Gaser, Christian, Huttunen, Heikki, Tohka, Jussi
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.01.2015; Elsevier Limited
• Subjects: ADNI; Age; Aged; Aged, 80 and over; Aggregates; Alzheimer Disease - pathology; Alzheimer's disease; Biomarkers; Brain - pathology; Classification; Cognitive Dysfunction - pathology; Conversion; Databases, Factual; Diagnosis; Early diagnosis; Feature selection; Female; Humans; Image Interpretation, Computer-Assisted - methods; Learning; Low density separation; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical imaging; Middle Aged; Mild cognitive impairment; NMR; Nuclear magnetic resonance; Patients; Risk Factors; Semi-supervised learning; Studies; Support vector machine; ADNI; Feature selection; Early diagnosis; Magnetic resonance imaging; Mild cognitive impairment; Semi-supervised learning; Classification; Low density separation; Support vector machine; Alzheimer's disease

Mild cognitive impairment (MCI) is a transitional stage between age-related cognitive decline and Alzheimer's disease (AD). For the effective treatment of AD, it would be important to identify MCI patients at high risk for conversion to AD. In this study, we present a novel magnetic resonance i...