HARP: HARmonizing in-vivo diffusion MRI using Phantom-only training

2026-03-05

AI Summary

This study addresses the challenge of harmonizing multicenter diffusion MRI (dMRI) data, which is hindered by scanner-induced variability and the scarcity of cross-site living subjects required by existing correction methods. The authors propose a deep learning–based harmonization framework that relies solely on portable diffusion phantom data, eliminating the need for multisite in vivo scans. By employing voxel-wise 1D neural networks to learn mappings between spherical harmonic coefficients across scanners, this approach achieves the first fully phantom-based dMRI harmonization. Experimental results demonstrate that the method substantially reduces inter-scanner variability in fractional anisotropy (FA; 12%), mean diffusivity (MD; 10%), and generalized fractional anisotropy (GFA; 30%), while accurately preserving fiber orientation and tractography quality. This advancement significantly enhances the feasibility and scalability of large-scale multicenter clinical dMRI studies.

Technology Category

• Machine Learning: Learning with Manifolds
• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Purpose: Combining multi-site diffusion MRI (dMRI) data is hindered by inter-scanner variability, which confounds subsequent analysis. Previous harmonization methods require large, matched or traveling human subjects from multiple sites, which are impractical to acquire in many situations. This study aims to develop a deep learning-based dMRI harmonization framework that eliminates the reliance on multi-site in-vivo traveling human data for training. Methods: HARP employs a voxel-wise 1D neural network trained on an easily transportable diffusion phantom. The model learns relationships between spherical harmonics coefficients of different sites without memorizing spatial structures. Results: HARP reduced inter-scanner variability levels significantly in various measures. Quantitatively, it decreased inter-scanner variability as measured by standard error in FA (12%), MD (10%), and GFA (30%) with scan-rescan standard error as the baseline, while preserving fiber orientations and tractography after harmonization. Conclusion: We believe that HARP represents an important first step toward dMRI harmonization using only phantom data, thereby obviating the need for complex, matched in vivo multi-site cohorts. This phantom-only strategy substantially enhances the feasibility and scalability of quantitative dMRI for large-scale clinical studies.

Problem

• diffusion MRI
• inter-scanner variability
• harmonization
• multi-site data
• phantom

Innovation

• diffusion MRI harmonization
• phantom-only training
• deep learning
• multi-site variability
• spherical harmonics