Evaluation of non-negative matrix factorization of grey matter in age prediction

Varikuti, Deepthi; Schwender, Holger; Hoffstaedter, Felix; Sotiras, Aristeidis; Caspers, Svenja; Davatzikos, Christos; Patil, Kaustubh; Jockwitz, Christiane; Amunts, Katrin; Eickhoff, Simon; Moebus, Susanne; Genon, Sarah

doi:10.1016/j.neuroimage.2018.03.007

Journal Article

FZJ-2018-01790

Evaluation of non-negative matrix factorization of grey matter in age prediction

Varikuti, D. (Corresponding author)FZJ* ; Genon, S.FZJ* ; Sotiras, A. ; Schwender, H. ; Hoffstaedter, F.FZJ* ; Patil, K.FZJ* ; Jockwitz, C.FZJ* ; Caspers, S.FZJ* ; Moebus, S. ; Amunts, K.FZJ* ; Davatzikos, C. ; Eickhoff, S.FZJ*

2018
Academic Press Orlando, Fla.

NeuroImage 173, 394-410 (2018) [10.1016/j.neuroimage.2018.03.007]

This record in other databases:

Please use a persistent id in citations: http://hdl.handle.net/2128/21476 doi:10.1016/j.neuroimage.2018.03.007

Abstract: The relationship between grey matter volume (GMV) patterns and age can be captured by multivariate pattern analysis, allowing prediction of individuals' age based on structural imaging. Raw data, voxel-wise GMV and non-sparse factorization (with Principal Component Analysis, PCA) show good performance but do not promote relatively localized brain components for post-hoc examinations. Here we evaluated a non-negative matrix factorization (NNMF) approach to provide a reduced, but also interpretable representation of GMV data in age prediction frameworks in healthy and clinical populations.This examination was performed using three datasets: a multi-site cohort of life-span healthy adults, a single site cohort of older adults and clinical samples from the ADNI dataset with healthy subjects, participants with Mild Cognitive Impairment and patients with Alzheimer's disease (AD) subsamples. T1-weighted images were preprocessed with VBM8 standard settings to compute GMV values after normalization, segmentation and modulation for non-linear transformations only. Non-negative matrix factorization was computed on the GM voxel-wise values for a range of granularities (50–690 components) and LASSO (Least Absolute Shrinkage and Selection Operator) regression were used for age prediction. First, we compared the performance of our data compression procedure (i.e., NNMF) to various other approaches (i.e., uncompressed VBM data, PCA-based factorization and parcellation-based compression). We then investigated the impact of the granularity on the accuracy of age prediction, as well as the transferability of the factorization and model generalization across datasets. We finally validated our framework by examining age prediction in ADNI samples.

Classification: