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

TL;DR

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 and substantially enhances the feasibility and scalability of quantitative dMRI for large-scale clinical studies.

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.

Figures (5)

• Figure 1: Conceptual overview of the HARP framework. (a) Comparison between conventional harmonization and the proposed HARP. Unlike traditional methods that necessitate the acquisition of matched or traveling human subject data from multiple sites, HARP utilizes easily accessible diffusion phantom data for network training. (b) Architectural overview of the 1D voxel-wise neural network. The network receives spherical harmonics coefficients from the source site as input and estimates harmonized spherical harmonics coefficients. This non-spatial architecture ensures robust generalizability when transferring the learned relationships from phantom training to in-vivo human inference.
• Figure 2: Voxel-wise standard error maps for GE $\rightarrow$ Siemens harmonization. The spatial distribution of standard errors for fractional anisotropy (FA), mean diffusivity (MD), and generalized fractional anisotropy (GFA) is displayed. Columns 1 and 2 represent the scan-rescan standard error for the source and target sites, respectively. Prior to harmonization (Column 3), the inter-scanner standard error is notably high across all metrics. The application of HARP (Column 5), which is trained exclusively on phantom data, results in a substantial reduction of standard error, achieving performance closer to the in-vivo-trained LinearRISH baseline (Column 4).
• Figure 3: Box plots illustrating the standard errors for averaged FA, MD, and GFA values across selected white matter regions of interest. The variability is categorized into source site scan-rescan (red), target site scan-rescan (yellow), inter-scanner without harmonization (blue), inter-scanner with LinearRISH (green), and inter-scanner with HARP (purple). Statistical significance from paired t-tests is indicated by *, **, and *** for p-values less than 0.05, 0.01, and 0.001, respectively. HARP significantly reduces the standard error across most tracts, with the exception of FA in the GE $\rightarrow$ Siemens scenario and MD in the Skyra $\rightarrow$ Prisma scenario at b = 1000 s/mm$^2$.
• Figure 4: Box plots illustrating the standard errors for averaged FA, MD, and GFA values across selected gray matter regions of interest. The color coding follows the same scheme as in Figure \ref{['fig:roiSE_wm']}: source site scan-rescan (red), target site scan-rescan (yellow), inter-scanner without harmonization (blue), inter-scanner with LinearRISH (green), and inter-scanner with HARP (purple). Significance levels are denoted by *, **, and *** for $p <$ 0.05, 0.01, and 0.001, respectively. In gray matter regions, HARP consistently and significantly reduces the inter-scanner standard error across all cases, demonstrating robust harmonization that aligns with the performance of the in-vivo-trained baseline.
• Figure 5: Visual comparison of (a) tractography (arcuate fasciculus and corticospinal tract) and (b) fiber orientation maps before (top) and after (bottom) HARP harmonization. The high consistency between rows confirms that the 1D voxel-wise framework preserves underlying fiber information.