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 Norgaard | 1 | 0 | 0.34 |
Douglas N. Greve | 2 | 777 | 49.66 |
Claus Svarer | 3 | 115 | 39.44 |
Stephen C. Strother | 4 | 399 | 56.31 |
Gitte M Knudsen | 5 | 30 | 7.91 |
Melanie Ganz | 6 | 25 | 6.87 |