Manifold population modeling as a neuro-imaging biomarker: Application to ADNI and ADNI-GO

• Published in: NeuroImage (Orlando, Fla.) Vol. 94; pp. 275 - 286
• Main Authors: Guerrero, R., Wolz, R., Rao, A.W., Rueckert, D.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.07.2014; Elsevier; Elsevier Limited
• Subjects: Adult and adolescent clinical studies; Aged; Aged, 80 and over; Algorithms; Alzheimer Disease - diagnosis; Alzheimer Disease - epidemiology; Alzheimer's disease; Alzheimer's disease (AD); Artificial Intelligence; Biological and medical sciences; Biomarkers; Brain - pathology; Causality; Classification; Clinical trials; Cognitive Dysfunction - diagnosis; Cognitive Dysfunction - epidemiology; Comorbidity; Computer Simulation; Degenerative and inherited degenerative diseases of the nervous system. Leukodystrophies. Prion diseases; Dementia; Female; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Kernel density estimation; Laplacian eigenmaps; Magnetic Resonance Imaging - methods; Male; Manifold learning; Medical imaging; Medical sciences; Middle Aged; Mild cognitive impairment (MCI); Models, Statistical; Neuroimaging - methods; Neurology; Older people; Organic mental disorders. Neuropsychology; Patients; Pattern Recognition, Automated - methods; Psychology. Psychoanalysis. Psychiatry; Psychopathology. Psychiatry; Reproducibility of Results; Sensitivity and Specificity; Sparse regression; Studies; Laplacian eigenmaps; Mild cognitive impairment (MCI); Classification; Alzheimer's disease (AD); Sparse regression; Manifold learning; Kernel density estimation; Nervous system diseases; Alzheimer disease; Biological marker; Density; Cerebral disorder; Learning; Acquisition process; Imaging; Central nervous system disease; Degenerative disease; mild cognitive impairment
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2014.03.036

We propose a framework for feature extraction from learned low-dimensional subspaces that represent inter-subject variability. The manifold subspace is built from data-driven regions of interest (ROI). The regions are learned via sparse regression using the mini-mental state examination (MMSE) score as an independent variable which correlates better with the actual disease stage than a discrete class label. The sparse regression is used to perform variable selection along with a re-sampling scheme to reduce sampling bias. We then use the learned manifold coordinates to perform visualization and classification of the subjects. Results of the proposed approach are shown using the ADNI and ADNI-GO datasets. Three types of classification techniques, including a new MRI Disease-State-Score (MRI-DSS) classifier, are tested in conjunction with two learning strategies. In the first case Alzheimer's Disease (AD) and progressive mild cognitive impairment (pMCI) subjects were grouped together, while cognitive normal (CN) and stable mild cognitive impaired (sMCI) subjects were also grouped together. In the second approach, the classifiers are learned using the original class labels (with no grouping). We show results that are comparable to other state-of-the-art methods. A classification rate of 71%, of arguably the most clinically relevant subjects, sMCI and pMCI, is shown. Additionally, we present classification accuracies between CN and early MCI (eMCI) subjects, from the ADNI-GO dataset, of 65%. To our knowledge this is the first time classification accuracies for eMCI patients have been reported. •Manifold learning from data-driven regions of interest•Encouraging classification results on ADNI and ADNI-GO datasets•Continuous disease modeling in the manifold using the proposed MRI-DSS biomarker•High MMSE prediction accuracy on the learned subspace