Dataset Information

The use of back propagation neural networks and 18F-Florbetapir PET for early detection of Alzheimer's disease using Alzheimer's Disease Neuroimaging Initiative database.

ABSTRACT: Amyloid beta (A?) plaques aggregation is considered as the "start" of the degenerative process that manifests years before the clinical symptoms appear in Alzheimer's Disease (AD). The aim of this study is to use back propagation neural networks (BPNNs) in 18F-florbetapir PET data for automated classification of four patient groups including AD, late mild cognitive impairment (LMCI), early mild cognitive impairment (EMCI), and significant memory concern (SMC), versus normal control (NC) for early AD detection. Five hundred images for AD, LMCI, EMCI, SMC, and NC, i.e., 100 images for each group, were used from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The results showed that the automated classification of NC/AD produced a high accuracy of 87.9%, while the results for the prodromal stages of the disease were 66.4%, 60.0%, and 52.9% for NC/LCMI, NC/EMCI and NC/SMC, respectively. The proposed method together with the image preparation steps can be used for early AD detection and classification with high accuracy using A? PET dataset.

SUBMITTER: Ozsahin I

PROVIDER: S-EPMC6932766 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The use of back propagation neural networks and 18F-Florbetapir PET for early detection of Alzheimer's disease using Alzheimer's Disease Neuroimaging Initiative database.

Ozsahin Ilker I Sekeroglu Boran B Mok Greta S P GSP

PloS one 20191226 12

Amyloid beta (Aβ) plaques aggregation is considered as the "start" of the degenerative process that manifests years before the clinical symptoms appear in Alzheimer's Disease (AD). The aim of this study is to use back propagation neural networks (BPNNs) in 18F-florbetapir PET data for automated classification of four patient groups including AD, late mild cognitive impairment (LMCI), early mild cognitive impairment (EMCI), and significant memory concern (SMC), versus normal control (NC) for earl ...[more]

PMID: 31877173

Similar Datasets

Project description:BackgroundBiomarkers based on the underlying pathology of Alzheimer's disease (AD) and Dementia with Lewy Bodies (DLB) have the potential to improve diagnosis and understanding of the substrate for cognitive impairment in these disorders. The objective of this study was to compare the patterns of amyloid and dopamine PET imaging in patients with AD, DLB and Parkinson's disease (PD) using the amyloid imaging agent florbetapir F 18 and 18F-AV-133 (florbenazine), a marker for vesicular monamine type 2 transporters (VMAT2).MethodsPatients with DLB and AD, Parkinson's disease (PD) and healthy controls (HC) were recruited for this study. On separate days, subjects received intravenous injections of florbetapir, and florbenazine. Amyloid burden and VMAT2 density were assessed quantitatively and by binary clinical interpretation. Imaging results for both tracers were compared across the four individual diagnostic groups and for combined groups based on underlying pathology (AD/DLB vs. PD/HC for amyloid burden and PD/DLB vs. AD/HC for VMAT binding) and correlated with measures of cognition and parkinsonism.Results11 DLB, 10 AD, 5 PD, and 5 controls participated in the study. Amyloid binding was significantly higher in the combined AD/DLB patient group (n = 21) compared to the PD/HC groups (n = 10, mean SUVr: 1.42 vs. 1.07; p = 0.0006). VMAT2 density was significantly lower in the PD/DLB group (n = 16) compared to the AD/ HC group (n = 15; 1.83 vs. 2.97; p < 0.0001). Within the DLB group, there was a significant correlation between cognitive performance and striatal florbenazine binding (r = 0.73; p = 0.011).ConclusionsThe results of this study show significant differences in both florbetapir and florbenazine imaging that are consistent with expected pathology. In addition, VMAT density correlated significantly with cognitive impairment in DLB patients (ClinicalTrials.gov identifier: NCT00857506, registered March 5, 2009).

Dataset Information

The use of back propagation neural networks and 18F-Florbetapir PET for early detection of Alzheimer's disease using Alzheimer's Disease Neuroimaging Initiative database.

Publications

The use of back propagation neural networks and 18F-Florbetapir PET for early detection of Alzheimer's disease using Alzheimer's Disease Neuroimaging Initiative database.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets