Performance Scaling for Structural MRI Surface Parcellations: A Machine Learning Analysis in the ABCD Study

BioRxiv : the Preprint Server for Biology
Sage HahnN. Allgaier


The use of pre-defined parcellations on surface-based representations of the brain as a method for data reduction is common across neuroimaging studies. In particular, prediction-based studies typically employ parcellation-driven summaries of brain measures as input to predictive algorithms, but the choice of parcellation and its influence on performance is often ignored. Here we employed pre-processed structural magnetic resonance imaging data (sMRI) from the ABCD Study to examine the relationship between 220 parcellations and out-of-sample predictive performance across 45 phenotypic measures in a large sample of 9-10-year-old children (N=9,432). Choice of Machine Learning (ML) pipeline and use of alternative multiple parcellation-based strategies were also assessed. Relative parcellation performance was dependent on the spatial resolution of the parcellation, with larger numbers of parcels (up to ~4000) outperforming coarser parcellations, according to a power-law scaling of between 1/4 and 1/3. Performance was further influenced by the type of parcellation, ML pipeline, and general strategy, with existing literature-based parcellations, a support vector based pipeline, and ensembling across multiple parcellations, respective...Continue Reading

Software Mentioned

Brain Predictability toolbox
Light Gradient Boosting Machine ( LGBM )
Human Connectome Project Workbench

Related Concepts

Related Feeds

BioRxiv & MedRxiv Preprints

BioRxiv and MedRxiv are the preprint servers for biology and health sciences respectively, operated by Cold Spring Harbor Laboratory. Here are the latest preprint articles (which are not peer-reviewed) from BioRxiv and MedRxiv.