Machine Learning-based Individual Assessment of Cortical Atrophy Pattern in Alzheimer’s Disease Spectrum: Development of the Classifier and Longitudinal Evaluation

Abstract

To develop a new method for measuring Alzheimer’s disease (AD)-specific similarity of cortical atrophy patterns at the individual-level, we employed an individual-level machine learning algorithm. A total of 869 cognitively normal (CN) individuals and 473 patients with probable AD dementia who underwent high-resolution 3T brain MRI were included. We propose a machine learning-based method for measuring the similarity of an individual subject’s cortical atrophy pattern with that of a representative AD patient cohort. In addition, we validated this similarity measure in two longitudinal cohorts consisting of 79 patients with amnestic-mild cognitive impairment (aMCI) and 27 patients with probable AD dementia. Surface-based morphometry classifier for discriminating AD from CN showed sensitivity and specificity values of 87.1% and 93.3%, respectively. In the longitudinal validation study, aMCI-converts had higher atrophy similarity at both baseline (p < 0.001) and first year visits (p < 0.001) relative to non-converters. Similarly, AD patients with faster decline had higher atrophy similarity than slower decliners at baseline (p = 0.042), first year (p = 0.028), and third year visits (p = 0.027). The AD-specific atrophy similarity measure is a novel approach for the prediction of dementia risk and for the evaluation of AD trajectories on an individual subject level.

Concordance in detecting amyloid positivity between 18F-florbetaben and 18F-flutemetamol amyloid PET using quantitative and qualitative assessments

“…FBB 18 F-florbetaben, FMM 18 F-flutemetamol, SUVR standardized uptake value ratio, CN cognitively normal, MCI mild cognitive impairment, ADD Alzheimer's disease dementia. a In previous research 9 , we analysed the cortical atrophy pattern for each subject based on the cortical thickness data and measure the AD-specific pattern similarity then calculated on an individual subject basis. www.nature.com/scientificreports/ www.nature.com/scientificreports/ SUVR cut-offs (iterative outlier method with old controls (OCs) in this study compared with the receiver operating characteristic method in previous studies).…”

“…In this case, differences between the two ligands in false-positive rate (1.8% vs. 9.1%, p = 0.13) and false-negative rate (10% vs. 6%, p = 0.5) were not observed. Previously, we developed a new method for measuring Alzheimer's disease (AD)-specific similarity of cortical atrophy patterns at the individual-level 9 . The AD-specific atrophy similarity score represents how similar the cortical atrophy pattern of an individual participant is to that of a representative AD patient.…”

Imaging biomarkers in neurodegeneration: current and future practices

“…The scatter plot (lower left) shows the correlation of regional Flortaucipir SUVR and object activation in posterior-medial regions. See Maass et al [158] for study details longitudinal studies analysed the progression of AD [188][189][190] using structural MRI and deep learning (DL) algorithms such as recurrent neural networks (RNNs) and variations of long short-term memory networks (LSTMN). The most common feature in order to study disease progression is hippocampal volume.…”

Comparison of Vendor-Provided Volumetry Software and NeuroQuant Using 3D T1-Weighted Images in Subjects with Cognitive Impairment: How Large is the Inter-Method Discrepancy?

“…Currently, several commercially available clinical volumetry software are being studied (5)(6)(7)(8). Diagnostic accuracy of these software has been extensively studied (4,(9)(10)(11).…”