Meta-analysis based SVM classification enables accurate detection of Alzheimer's disease across different clinical centers using FDG-PET and MRI.

The application of support vector machine classification (SVM) to combined information from magnetic resonance imaging (MRI) and [F18]fluorodeoxyglucose positron emission tomography (FDG-PET) has been shown to improve detection and differentiation of Alzheimer's disease dementia (AD) and frontotemporal lobar degeneration. To validate this approach for the most frequent dementia syndrome AD, and to test its applicability to multicenter data, we randomly extracted FDG-PET and MRI data of 28 AD patients and 28 healthy control subjects from the database provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI) and compared them to data of 21 patients with AD and 13 control subjects from our own Leipzig cohort. SVM classification using combined volume-of-interest information from FDG-PET and MRI based on comprehensive quantitative meta-analyses investigating dementia syndromes revealed a higher discrimination accuracy in comparison to single modality classification. For the ADNI dataset accuracy rates of up to 88% and for the Leipzig cohort of up to 100% were obtained. Classifiers trained on the ADNI data discriminated the Leipzig cohorts with an accuracy of 91%. In conclusion, our results suggest SVM classification based on quantitative meta-analyses of multicenter data as a valid method for individual AD diagnosis. Furthermore, combining imaging information from MRI and FDG-PET might substantially improve the accuracy of AD diagnosis.

Reference Cluster Normalization Improves Detection of Frontotemporal Lobar Degeneration by Means of FDG-PET.

Positron emission tomography with [18F] fluorodeoxyglucose (FDG-PET) plays a well-established role in assisting early detection of frontotemporal lobar degeneration (FTLD). Here, we examined the impact of intensity normalization to different reference areas on accuracy of FDG-PET to discriminate between patients with mild FTLD and healthy elderly subjects. FDG-PET was conducted at two centers using different acquisition protocols: 41 FTLD patients and 42 controls were studied at center 1, 11 FTLD patients and 13 controls were studied at center 2. All PET images were intensity normalized to the cerebellum, primary sensorimotor cortex (SMC), cerebral global mean (CGM), and a reference cluster with most preserved FDG uptake in the aforementioned patients group of center 1. Metabolic deficits in the patient group at center 1 appeared 1.5, 3.6, and 4.6 times greater in spatial extent, when tracer uptake was normalized to the reference cluster rather than to the cerebellum, SMC, and CGM, respectively. Logistic regression analyses based on normalized values from FTLD-typical regions showed that at center 1, cerebellar, SMC, CGM, and cluster normalizations differentiated patients from controls with accuracies of 86%, 76%, 75% and 90%, respectively. A similar order of effects was found at center 2. Cluster normalization leads to a significant increase of statistical power in detecting early FTLD-associated metabolic deficits. The established FTLD-specific cluster can be used to improve detection of FTLD on a single case basis at independent centers - a decisive step towards early diagnosis and prediction of FTLD syndromes enabling specific therapies in the future.

Prevalence of cerebral amyloid pathology in persons without dementia: a meta-analysis.

IMPORTANCE: Cerebral amyloid-β aggregation is an early pathological event in Alzheimer disease (AD), starting decades before dementia onset. Estimates of the prevalence of amyloid pathology in persons without dementia are needed to understand the development of AD and to design prevention studies. OBJECTIVE: To use individual participant data meta-analysis to estimate the prevalence of amyloid pathology as measured with biomarkers in participants with normal cognition, subjective cognitive impairment (SCI), or mild cognitive impairment (MCI). DATA SOURCES: Relevant biomarker studies identified by searching studies published before April 2015 using the MEDLINE and Web of Science databases and through personal communication with investigators. STUDY SELECTION: Studies were included if they provided individual participant data for participants without dementia and used an a priori defined cutoff for amyloid positivity. DATA EXTRACTION AND SYNTHESIS: Individual records were provided for 2914 participants with normal cognition, 697 with SCI, and 3972 with MCI aged 18 to 100 years from 55 studies. MAIN OUTCOMES AND MEASURES: Prevalence of amyloid pathology on positron emission tomography or in cerebrospinal fluid according to AD risk factors (age, apolipoprotein E [APOE] genotype, sex, and education) estimated by generalized estimating equations. RESULTS: The prevalence of amyloid pathology increased from age 50 to 90 years from 10% (95% CI, 8%-13%) to 44% (95% CI, 37%-51%) among participants with normal cognition; from 12% (95% CI, 8%-18%) to 43% (95% CI, 32%-55%) among patients with SCI; and from 27% (95% CI, 23%-32%) to 71% (95% CI, 66%-76%) among patients with MCI. APOE-ε4 carriers had 2 to 3 times higher prevalence estimates than noncarriers. The age at which 15% of the participants with normal cognition were amyloid positive was approximately 40 years for APOE ε4ε4 carriers, 50 years for ε2ε4 carriers, 55 years for ε3ε4 carriers, 65 years for ε3ε3 carriers, and 95 years for ε2ε3 carriers. Amyloid positivity was more common in highly educated participants but not associated with sex or biomarker modality. CONCLUSIONS AND RELEVANCE: Among persons without dementia, the prevalence of cerebral amyloid pathology as determined by positron emission tomography or cerebrospinal fluid findings was associated with age, APOE genotype, and presence of cognitive impairment. These findings suggest a 20- to 30-year interval between first development of amyloid positivity and onset of dementia.