Learning Multi-Site Harmonization of Magnetic Resonance Images Without Traveling Human Phantoms

TL;DR

This paper introduces a deep learning method for harmonizing multi-site MRI data without needing traveling human phantoms, enabling effective retrospective data harmonization across diverse scanners and protocols.

Contribution

A novel deep neural network approach that disentangles site-specific and site-invariant features to harmonize MRI images without requiring same-subject data across sites.

Findings

Effective in generating realistic site-specific MRI images

Works with over 6,000 multi-site images

Enables retrospective data harmonization

Abstract

Harmonization improves data consistency and is central to effective integration of diverse imaging data acquired across multiple sites. Recent deep learning techniques for harmonization are predominantly supervised in nature and hence require imaging data of the same human subjects to be acquired at multiple sites. Data collection as such requires the human subjects to travel across sites and is hence challenging, costly, and impractical, more so when sufficient sample size is needed for reliable network training. Here we show how harmonization can be achieved with a deep neural network that does not rely on traveling human phantom data. Our method disentangles site-specific appearance information and site-invariant anatomical information from images acquired at multiple sites and then employs the disentangled information to generate the image of each subject for any target site. We demonstrate with more than 6,000 multi-site T1- and T2-weighted images that our method is remarkably effective in generating images with realistic site-specific appearances without altering anatomical details. Our method allows retrospective harmonization of data in a wide range of existing modern large-scale imaging studies, conducted via different scanners and protocols, without additional data collection.