Predicting Brain Amyloid using Multivariate Morphometry Statistics, Sparse Coding, and Correntropy: Validation in 1,101 Individuals from the ADNI and OASIS Databases

Abstract

Biomarker-assisted preclinical/early detection and intervention in Alzheimers disease (AD) may be the key to therapeutic breakthroughs. One of the presymptomatic hallmarks of AD is the accumulation of beta-amyloid (A{beta}) plaques in the human brain. However, current methods to detect A{beta} pathology are either invasive (lumbar puncture) or quite costly and not widely available (amyloid PET). Our prior studies show that MRI-based hippocampal multivariate morphometry statistics (MMS) are an effective neurodegenerative biomarker for preclinical AD. Here we attempt to use MRI-MMS to make inferences regarding brain A{beta} burden at the individual subject level. As MMS data has a larger dimension than the sample size, we propose a sparse coding algorithm, Patch Analysis-based Surface Correntropy-induced Sparse coding and max-pooling (PASCS-MP), to generate a low-dimensional representation of hippocampal morphometry for each subject. Then we apply these individual representations and a binary random forest classifier to predict brain A{beta} positivity for each person. We test our method in two independent cohorts, 841 subjects from the Alzheimers Disease Neuroimaging Initiative (ADNI) and 260 subjects from the Open Access Series of Imaging Studies (OASIS). Experimental results suggest that our proposed PASCS-MP method and MMS can discriminate A{beta} positivity in people with mild cognitive impairment (MCI) (Accuracy (ACC)=0.89 (ADNI)) and in cognitively unimpaired (CU) individuals (ACC=0.79 (ADNI) and ACC=0.81 (OASIS)). These results compare favorably relative to measures derived from traditional algorithms, including hippocampal volume and surface area, shape measures based on spherical harmonics (SPHARM), and our prior Patch Analysis-based Surface Sparse-coding and Max-Pooling (PASS-MP) methods.