Distance-informed metric learning for Alzheimer's disease staging

• Published in: 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society Vol. 2014; pp. 934 - 937
• Main Authors: Shi, Bibo, Wang, Zhewei, Liu, Jundong
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.01.2014
• Subjects: Algorithms; Alzheimer Disease - diagnosis; Alzheimer Disease - pathology; Alzheimer's disease; Case-Control Studies; Cognitive Dysfunction - diagnosis; Feature extraction; Humans; Magnetic resonance imaging; Measurement; Neuroimaging; Shape
• ISSN: 1094-687X; 1557-170X
• DOI: 10.1109/EMBC.2014.6943745

Identifying intermediate biomarkers of Alzheimer's disease (AD) is of great importance for diagnosis and prognosis of the disease. In this study, we develop a new AD staging method to classify patients into Normal Controls (NC), Mild Cognitive Impairment (MCI), and AD groups. Our solution employs a novel metric learning technique that improves classification rates through the guidance of some weak supervisory information in AD progression. More specifically, those information are in the form of pairwise constraints that specify the relative Mini Mental State Examination (MMSE) score disparity of two subjects, depending on whether they are in the same group or not. With the imposed constraints, the common knowledge that MCI generally sits in between of NC and AD can be integrated into the classification distance metric. Subjects from the Alzheimer's Disease Neuroimaging Initiative cohort (ADNI; 56 AD, 104 MCI, 161 controls) were used to demonstrate the improvements made comparing with two state-of-the-art metric learning solutions: large margin nearest neighbors (LMNN) and relevant component analysis (RCA).