Support vector machine-based classification of Alzheimer’s disease from whole-brain anatomical MRI

• Published in: Neuroradiology Vol. 51; no. 2; pp. 73 - 83
• Main Authors: Magnin, Benoît, Mesrob, Lilia, Kinkingnéhun, Serge, Pélégrini-Issac, Mélanie, Colliot, Olivier, Sarazin, Marie, Dubois, Bruno, Lehéricy, Stéphane, Benali, Habib
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer-Verlag 01.02.2009; Springer; Springer Nature B.V; Springer Verlag
• Subjects: Aged; Algorithms; Alzheimer Disease - pathology; Alzheimer's disease; Anatomy & physiology; Artificial Intelligence; Biological and medical sciences; Brain; Brain - pathology; Computer Science; Degenerative and inherited degenerative diseases of the nervous system. Leukodystrophies. Prion diseases; Diagnostic Neuroradiology; Female; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Imaging; Investigative techniques, diagnostic techniques (general aspects); Magnetic Resonance Imaging - methods; Male; Medical diagnosis; Medical Imaging; Medical sciences; Medicine; Medicine & Public Health; Nervous system; Neurology; Neuroradiology; Neurosciences; Neurosurgery; NMR; Nuclear magnetic resonance; Pattern Recognition, Automated - methods; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Radiology; Reproducibility of Results; Sensitivity and Specificity; Sensitivity; Specificity; Diagnosis; Support vector machine; Alzheimer’s disease; Magnetic resonance image; Nervous system diseases; Radiodiagnosis; Alzheimer disease; Magnetic resonance; Central nervous system; Nuclear magnetic resonance imaging; Cerebral disorder; Encephalon; Central nervous system disease; Classification; Degenerative disease; Vector; Alzheimer's disease
• ISSN: 0028-3940; 1432-1920; 1432-1920
• DOI: 10.1007/s00234-008-0463-x

Purpose We present and evaluate a new automated method based on support vector machine (SVM) classification of whole-brain anatomical magnetic resonance imaging to discriminate between patients with Alzheimer’s disease (AD) and elderly control subjects. Materials and methods We studied 16 patients with AD [mean age ± standard deviation (SD) = 74.1 ± 5.2 years, mini-mental score examination (MMSE) = 23.1 ± 2.9] and 22 elderly controls (72.3 ± 5.0 years, MMSE = 28.5 ± 1.3). Three-dimensional T1-weighted MR images of each subject were automatically parcellated into regions of interest (ROIs). Based upon the characteristics of gray matter extracted from each ROI, we used an SVM algorithm to classify the subjects and statistical procedures based on bootstrap resampling to ensure the robustness of the results. Results We obtained 94.5% mean correct classification for AD and control subjects (mean specificity, 96.6%; mean sensitivity, 91.5%). Conclusions Our method has the potential in distinguishing patients with AD from elderly controls and therefore may help in the early diagnosis of AD.