Inter-modality relationship constrained multi-modality multi-task feature selection for Alzheimer's Disease and mild cognitive impairment identification

• Published in: NeuroImage (Orlando, Fla.) Vol. 84; pp. 466 - 475
• Main Authors: Liu, Feng, Wee, Chong-Yaw, Chen, Huafu, Shen, Dinggang
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.01.2014; Elsevier; Elsevier Limited
• Subjects: Adult and adolescent clinical studies; Aged; Aged, 80 and over; Alzheimer Disease - diagnosis; Alzheimer's Disease; Artificial Intelligence; Biological and medical sciences; Cognitive Dysfunction - diagnosis; Degenerative and inherited degenerative diseases of the nervous system. Leukodystrophies. Prion diseases; Diagnosis, Differential; Female; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Inter-modality relationship; Magnetic Resonance Imaging - methods; Male; Medical research; Medical sciences; Middle Aged; Mild cognitive impairment; Multi-kernel support vector machine; Multi-task feature selection; Neurology; Organic mental disorders. Neuropsychology; Pattern Recognition, Automated - methods; Pharmaceutical industry; Positron-Emission Tomography - methods; Psychology. Psychoanalysis. Psychiatry; Psychopathology. Psychiatry; Reproducibility of Results; Sensitivity and Specificity; Studies; Multi-task feature selection; Inter-modality relationship; Alzheimer's Disease; Mild cognitive impairment; Multi-kernel support vector machine; Nervous system diseases; Alzheimer disease; Central nervous system disease; Degenerative disease; mild cognitive impairment; Cerebral disorder

Previous studies have demonstrated that the use of integrated information from multi-modalities could significantly improve diagnosis of Alzheimer's Disease (AD). However, feature selection, which is one of the most important steps in classification, is typically performed separately for each m...