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

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.

Reproducibility of sodium MRI measures of articular cartilage of the knee in osteoarthritis.

OBJECTIVE: To determine the stability and reproducibility of the sodium magnetic resonance imaging (MRI) signal measured in the articular cartilage of the knee in both healthy volunteers and osteoarthritis (OA) patients. DESIGN: This was a prospective Research Ethics Committee approved study that acquired sodium and proton MRI data from 15 subjects with OA (three males, age 64 ± 10) and five healthy controls age and sex matched over the group. Each subject underwent standing planar radiographs of their knees for radiological scoring as well as symptomatological assessment questionnaires. In two MRI sessions on the same day, high resolution double-echo steady state (DESS) and 3D short echo time sodium MRI images of the most diseased knee were acquired and co-registered in each session. A blinded reader (LT) manually delineated the articular cartilage into four discrete regions, and two combined regions, on the DESS images. These regions were applied to the sodium images, and a median sodium signal from each reported. Within-subject and between-subject coefficients of variation were estimated and intraclass correlation coefficients for the healthy control group, OA subject group, and all pooled subjects group were calculated. RESULTS: Within-subject variability of sodium MRI at 3T was 3.2% overall, and 2.0% in healthy age-matched volunteers compared to a reproducibility of 3.6% on OA subjects. CONCLUSIONS: The reproducibility of sodium MRI was similar in both healthy controls and OA subjects. Researchers piloting techniques in healthy controls thus may expect a similar reproducibility in a controlled trial involving subjects with American College of Rheumatology (ACR)-defined OA of the knee.

Pragmatic study of orlistat 60 mg on abdominal obesity.

BACKGROUND/OBJECTIVES: It is well established that combining a reduced calorie, low-fat diet with the lipase inhibitor orlistat results in significantly greater weight loss than placebo plus diet. This weight loss is accompanied by changes in adipose tissue (AT) distribution. As 60 mg orlistat is now available as an over-the-counter medication, the primary objective of this study was to determine whether 60 mg orlistat is effective as a weight loss option in a free-living community population with minimal professional input. METHODS: AT and ectopic lipid content were measured using magnetic resonance imaging and (1)H MR spectroscopy, respectively, in 27 subjects following 3 months treatment with orlistat 60 mg and a reduced calorie, low-fat diet. RESULTS: Significant reductions in intra-abdominal AT (-10.6%, P=0.023), subcutaneous (-11.7% P<0.0001) and pericardial fat (-9.8%, P=0.034) volumes and intrahepatocellular lipids (-43.3%, P=0.0003) were observed. These changes in body fat content and distribution were accompanied by improvements in plasma lipids and decreases in blood pressure and heart rate. CONCLUSION: These findings suggest that over-the-counter 60 mg orlistat, in combination with the type of advice a subject could expect to be given when obtaining 60 mg orlistat in a community setting, does indeed result in potentially clinically beneficial changes in body composition and risk factors for metabolic diseases.