Data-driven, voxel-based analysis of brain PET images: Application of PCA and LASSO methods to visualize and quantify patterns of neurodegeneration

Abstract

Spatial patterns of radiotracer binding in positron emission tomography (PET) images may convey information related to the disease topology. However, this information is not captured by the standard PET image analysis that quantifies the mean radiotracer uptake within a region of interest (ROI). On the other hand, spatial analyses that use more advanced radiomic features may be difficult to interpret. Here we propose an alternative data-driven, voxel-based approach to spatial pattern analysis in brain PET, which can be easily interpreted. We apply principal component analysis (PCA) to identify voxel covariance patterns, and optimally combine several patterns using the least absolute shrinkage and selection operator (LASSO). The resulting models predict clinical disease metrics from raw voxel values, allowing for inclusion of clinical covariates. The analysis is performed on high-resolution PET images from healthy controls and subjects affected by Parkinson’s disease (PD), acquired with a pre-synaptic and a post-synaptic dopaminergic PET tracer. We demonstrate that PCA identifies robust and tracer-specific binding patterns in sub-cortical brain structures; the patterns evolve as a function of disease progression. Principal component LASSO (PC-LASSO) models of clinical disease metrics achieve higher predictive accuracy compared to the mean tracer binding ratio (BR) alone: the cross-validated test mean squared error of adjusted disease duration (motor impairment score) was 16.3 ± 0.17 years2 (9.7 ± 0.15) with mean BR, versus 14.4 ± 0.18 years2 (8.9 ± 0.16) with PC-LASSO. We interpret the best-performing PC-LASSO models in the spatial sense and discuss them with reference to the PD pathology and somatotopic organization of the striatum. PC-LASSO is thus shown to be a useful method to analyze clinically-relevant tracer binding patterns, and to construct interpretable, imaging-based predictive models of clinical metrics.

Joint pattern analysis applied to PET DAT and VMAT2 imaging reveals new insights into Parkinson's disease induced presynaptic alterations

“…It seeks two mixing matrices (W 1 and W 2 ) such that each pair of canonical variates U i and V i ( i = 1…5) has maximum correlation across the two datasets, while the canonical variates within each dataset are orthogonal (U i and U j are uncorrelated)For i = 1…5,maxW1i,W2iitaliccorr(),Xnormalwitalichiten×W1iYwhiten×W2iUi=Xwhiten×W1i;Vi=Ywhiten×W2iThus, the transformed data (canonical variates U and V) contain common (maximally correlated between two datasets) subject profiles, which are composed of subject score of each subject (representing the subject weights for the corresponding mixing matrix). Subject scores are in Z -score form with a mean of zero and a standard deviation of one.Least absolute shrinkage and selection operator (LASSO) (Klyuzhin et al, 2018a; Tibshirani, 2011) is then applied to regress the canonical variates (U i and V i ) from the original datasets X and Y to compute regression coefficients (CCA weights A and B) and regression residuals (X residual and Y residual ) as shown in Fig. 2.…”

“…Least absolute shrinkage and selection operator (LASSO) (Klyuzhin et al, 2018a; Tibshirani, 2011) is then applied to regress the canonical variates (U i and V i ) from the original datasets X and Y to compute regression coefficients (CCA weights A and B) and regression residuals (X residual and Y residual ) as shown in Fig. 2.…”

An improved approach for fault detection by simultaneous overcoming of high-dimensionality, autocorrelation, and time-variability

“…PCA converts a set of correlated variables into a smaller number of uncorrelated new variables, where the new sample includes the most information from the original data [ 2 , 23 , 24 ]. Let X ∈ R n × m be the original data matrix with n samples and m variables, which can be explained as: …”

Regional SUV quantification in hybrid PET/MR, a comparison of two atlas-based automatic brain segmentation methods

“…Previous studies have shown that the metabolic patterns of Parkinson's disease (PD) and atypical Parkinson's syndrome, e.g., multiple system atrophy (MSA), progressive supranuclear palsy (PSP), and corticobasal degeneration (CBD), were different [11]. However, it is usually difficult to quantitatively analyze abnormalities in different brain regions accurately [12]. Because of PET's relatively low spatial resolution and the complexities of brain anatomy, the analysis of regional PET quantification relies on MRI.…”