Data-driven, voxel-based analysis of brain PET images: Application of PCA and LASSO methods to visualize and quantify patterns of neurodegeneration
| Autor: | A. Jon Stoessl, Matthew A. Sacheli, Michele Matarazzo, Jessie Fanglu Fu, Andy Hong, Arman Rahmim, Vesna Sossi, Ivan S. Klyuzhin, Nikolay Shenkov |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Male
Computer science lcsh:Medicine Striatum computer.software_genre Biochemistry Diagnostic Radiology Pattern Recognition Automated 030218 nuclear medicine & medical imaging Mathematical and Statistical Techniques 0302 clinical medicine Lasso (statistics) Voxel Medicine and Health Sciences lcsh:Science Tomography Principal Component Analysis Movement Disorders Multidisciplinary medicine.diagnostic_test Radiology and Imaging Statistics Neurodegeneration Brain Neurodegenerative Diseases Parkinson Disease Neurochemistry Middle Aged Magnetic Resonance Imaging Neurology Positron emission tomography Physical Sciences Principal component analysis Pattern recognition (psychology) Female Neurochemicals Anatomy Research Article Adult Imaging Techniques Neuroimaging Research and Analysis Methods 03 medical and health sciences Spatio-Temporal Analysis Diagnostic Medicine Region of interest Image Interpretation Computer-Assisted Covariate medicine Humans Statistical Methods Least-Squares Analysis Aged business.industry lcsh:R Biology and Life Sciences Pattern recognition medicine.disease Neostriatum Case-Control Studies Positron-Emission Tomography Multivariate Analysis Nerve Degeneration lcsh:Q Artificial intelligence business Dopaminergics computer Positron Emission Tomography Mathematics 030217 neurology & neurosurgery Neuroscience |
| Zdroj: | PLoS ONE, Vol 13, Iss 11, p e0206607 (2018) PLoS ONE |
| ISSN: | 1932-6203 |
| DOI: | 10.1371/journal.pone.0206607 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|