deepmriprep: voxel-based morphometry preprocessing via deep neural networks.
Authors
Affiliations (11)
Affiliations (11)
- Institute for Translational Psychiatry, University of Münster, Münster, Germany. [email protected].
- Institute for Translational Psychiatry, University of Münster, Münster, Germany.
- Department of Psychiatry and Neuroscience, Campus Benjamin Franklin, Charité-Universitätsmedizin Berlin, Berlin, Germany.
- Institute for Geoinformatics, University of Münster, Münster, Germany.
- Faculty of Mathematics and Computer Science, University of Münster, Münster, Germany.
- Institute for Translational Neuroscience, University of Münster, Münster, Germany.
- Department of Psychiatry and Psychotherapy, University of Marburg, Marburg, Germany.
- Institute of Epidemiology and Social Medicine, University of Münster, Münster, Germany.
- Department of Psychiatry, Medical School and University Medical Center OWL, Protestant Hospital of the Bethel Foundation, Bielefeld University, Bielefeld, Germany.
- German Center for Mental Health (DZPG), Site Jena Magdeburg Halle, Berlin, Germany.
- Center for Intervention and Research on Adaptive and Maladaptive Brain Circuits Underlying Mental Health (C-I-R-C), Site Jena Magdeburg Halle, Jena, Germany.
Abstract
Voxel-based morphometry (VBM), a popular approach in neuroimaging research, uses magnetic resonance imaging data to assess variations in the local density of brain tissue and to examine its associations with biological and psychometric variables. Here we present deepmriprep, a preprocessing pipeline designed to leverage neural networks to perform all the necessary preprocessing steps for the VBM analysis of T<sub>1</sub>-weighted magnetic resonance imaging. Utilizing the graphics processing unit, deepmriprep is 37 times faster than CAT12, the leading VBM preprocessing toolbox. The proposed method matches CAT12 in accuracy for tissue segmentation and image registration across more than 100 datasets and shows strong correlations in the VBM results. Tissue segmentation maps from deepmriprep have more than 95% agreement with ground-truth maps, and its nonlinear registration predicts smooth deformation fields comparable to CAT12. The high computational speed of deepmriprep enables rapid preprocessing of large datasets and opens the door to real-time applications.