Clinical-ComBAT: a diffusion-weighted MRI harmonization method for clinical applications

2025-11-06

AI Summary

Multi-center diffusion-weighted MRI (DW-MRI) scalar maps suffer from site-specific biases due to scanner heterogeneity, undermining cross-site comparability. Existing ComBAT methods rely on restrictive assumptions—including linearity, population homogeneity, fixed site count, and sufficient sample size—limiting adaptability to dynamic clinical deployment. Method: We propose an enhanced Bayesian harmonization framework that replaces linear regression with nonlinear polynomial modeling; uses a normative site as reference for site-agnostic correction; incorporates small-sample–robust variance priors and adaptive hyperparameter tuning; and embeds goodness-of-fit evaluation. Contribution/Results: Evaluated on both synthetic and real multi-center DW-MRI data, our method significantly improves cross-site consistency of diffusion metrics (e.g., fractional anisotropy [FA], mean diffusivity [MD]). It enhances comparability, robustness, and scalability of multi-site data for neurodegenerative disease modeling and clinical translation.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Diffusion-weighted magnetic resonance imaging (DW-MRI) derived scalar maps are effective for assessing neurodegenerative diseases and microstructural properties of white matter in large number of brain conditions. However, DW-MRI inherently limits the combination of data from multiple acquisition sites without harmonization to mitigate scanner-specific biases. While the widely used ComBAT method reduces site effects in research, its reliance on linear covariate relationships, homogeneous populations, fixed site numbers, and well populated sites constrains its clinical use. To overcome these limitations, we propose Clinical-ComBAT, a method designed for real-world clinical scenarios. Clinical-ComBAT harmonizes each site independently, enabling flexibility as new data and clinics are introduced. It incorporates a non-linear polynomial data model, site-specific harmonization referenced to a normative site, and variance priors adaptable to small cohorts. It further includes hyperparameter tuning and a goodness-of-fit metric for harmonization assessment. We demonstrate its effectiveness on simulated and real data, showing improved alignment of diffusion metrics and enhanced applicability for normative modeling.

Problem

• Harmonizing diffusion MRI data across multiple clinical sites with scanner biases
• Overcoming ComBAT's limitations for real-world clinical applications and small cohorts
• Enabling flexible integration of new clinical data without population homogeneity requirements

Innovation

• Independent site harmonization for clinical flexibility
• Non-linear polynomial model with normative referencing
• Adaptive variance priors for small cohort compatibility