BARTharm: MRI Harmonization Using Image Quality Metrics and Bayesian Non-parametric
Preprint
Abstract
Image derived phenotypes (IDPs) harmonization from Magnetic Resonance Imaging (MRI) data is essential for reducing scanner-induced, non-biological variability and enabling accurate multi-site analysis. Existing methods like ComBat, while widely used, rely on linear assumptions and explicit scanner IDs - limitations that reduce their effectiveness in real-world scenarios involving complex scanner effects, non-linear biological variation, or anonymized data. We introduce BARTharm, a novel harmonization framework that uses Image Quality Metrics (IQMs) instead of Scanner IDs and models scanner and biological effects separately using Bayesian Additive Regression Trees (BART), allowing for flexible, data-driven adjustment of IDPs. Through extensive simulation studies, we demonstrate that IQMs provide a more informative and flexible representation of scanner-related variation than categorical Scanner IDs, enabling more accurate removal of non-biological effects. Leveraging this and its ability to model complex relationships, BARTharm, consistently outperforms ComBat across a range of challenging scenarios, including model misspecification and confounded scanner-biological relationships. Applied to real-world datasets, BARTharm successfully removes scanner-induced bias while preserving meaningful biological signals, resulting in stronger, more reliable associations with clinical outcomes. Overall, we find that BARTharm is a robust, data-driven improvement over traditional harmonization approaches, particularly suited for modern, large-scale neuroimaging studies.Keywords
Funding Information
- EPSRC Centre for Doctoral Training in Health Data Science (EP/S02428X/1)
This publication has 38 references indexed in Scilit:
- DeepResBat: Deep residual batch harmonization accounting for covariate distribution differencesMedical Image Analysis, 2024
- Multicenter data harmonization for regional brain atrophy and application in multiple sclerosisJournal of Neurology, 2022
- The alterations of brain functional connectivity networks in major depressive disorder detected by machine learning through multisite rs-fMRI dataBehavioural Brain Research, 2022
- Mitigating site effects in covariance for machine learning in neuroimaging dataHuman Brain Mapping, 2021
- Scanner invariant representations for diffusion MRI harmonizationMagnetic Resonance in Medicine, 2020
- Bayesian additive regression trees and the General BART modelStatistics in Medicine, 2019
- Effect of scanner in longitudinal studies of brain volume changesJournal of Magnetic Resonance Imaging, 2011
- Reliability of MRI-derived measurements of human cerebral cortical thickness: The effects of field strength, scanner upgrade and manufacturerNeuroImage, 2006
- Reliability in multi-site structural MRI studies: Effects of gradient non-linearity correction on phantom and human dataNeuroImage, 2006
- Impact of acquisition protocols and processing streams on tissue segmentation of T1 weighted MR imagesNeuroImage, 2006