Neuroharmony: A new tool for harmonizing volumetric MRI data from unseen scanners

TLDR

Neuroharmony is a harmonization tool designed to process volumetric MRI data from previously unseen scanners. Neuroharmony was developed using 15,026 structural MRI images to learn scanner‑invariant representations. The tool effectively reduces scanner‑related bias in unseen scans, represents a significant step toward imaging‑based clinical tools, and is available on GitHub.

Abstract

• We present Neuroharmony, a harmonization tool for images from unseen scanners. • We developed Neuroharmony using a total of 15,026 sMRI images. • The tool was able to reduce scanner-related bias from unseen scans. • Neuroharmony represents a significant step towards imaging-based clinical tools. • Neuroharmony is available at https://github.com/garciadias/Neuroharmony .