Paper Info
Title
The Impact of Preprocessing Pipeline Choice in Univariate and Multivariate Analyses of PET Data
Abstract
It has long been recognized that the data preprocessing chain is a critical part of a neuroimaging experiment. In this work we evaluate the impact of preprocessing choices in univariate and multivariate analyses of Positron Emission Tomography (PET) data. Thirty healthy participants were scanned twice in a High-Resolution Research Tomography PET scanner with the serotonin transporter (5-HTT) radioligand [ <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">11</sup> C]DASB. Binding potentials (BP <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ND</sub> ) from 14 brain regions are quantified with 384 different preprocessing choices. A univariate paired t-test is applied to each region and for each preprocessing choice, and corrected for multiple comparisons using FDR within each pipeline. Additionally, a multivariate Linear Discriminant Analysis (LDA) model is used to discriminate test and retest BP <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ND</sub> , and the model performance is evaluated using a repeated cross-validation framework with permutations. The univariate analysis revealed several significant differences in 5-HTT BP <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ND</sub> across brain regions, depending on the preprocessing choice. The classification accuracy of the multivariate LDA model varied from 37% to 70% depending on the choice of preprocessing, and could reasonably be modeled with a normal distribution centered at 51% accuracy. In spite of correcting for multiple comparisons, the univariate model with varying preprocessing choices is more likely to generate false-positive results compared to a simple multivariate analysis model evaluated with cross-validation and permutations.
Year
DOI
Venue
2018
10.1109/PRNI.2018.8423962
2018 International Workshop on Pattern Recognition in Neuroimaging (PRNI)
Keywords
Field
DocType
PET data,data preprocessing chain,neuroimaging experiment,multivariate analyses,serotonin transporter radioligand,multivariate Linear Discriminant Analysis model,univariate analysis,multivariate LDA model,univariate model,preprocessing pipeline,positron emission tomography data,high-resolution research tomography PET scanner
Normal distribution,Pattern recognition,Multivariate statistics,Multiple comparisons problem,Preprocessor,Artificial intelligence,Linear discriminant analysis,Univariate,Multivariate analysis,Mathematics,Univariate analysis
Conference
ISBN
Citations 
PageRank 
978-1-5386-6860-3
0
0.34
References 
Authors
3
6
Name
Order
Citations
PageRank
Martin Norgaard100.34
Douglas N. Greve277749.66
Claus Svarer311539.44
Stephen C. Strother439956.31
Gitte M Knudsen5307.91
Melanie Ganz6256.87