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

TL;DR

HARP is a deep learning framework that harmonizes multi-site diffusion MRI data using only phantom scans, eliminating the need for multi-site human data and improving consistency across scanners.

Contribution

HARP introduces a novel phantom-only training approach for dMRI harmonization, removing the dependency on multi-site in-vivo data for model training.

Findings

Significantly reduces inter-scanner variability in dMRI metrics.

Preserves fiber orientations and tractography post-harmonization.

Achieves this with a simple voxel-wise neural network trained on phantoms.

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.