Harmonizing MR Images Across 100+ Scanners: Multi-site Validation with Traveling Subjects and Real-world Protocols

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hays, Savannah P., Zuo, Lianrui, Chaudhary, Muhammad Faizyab Ali, Bartz, Kathleen M., Remedios, Samuel W., Zhang, Jinwei, Zhuo, Jiachen, Bilgel, Murat, Saidha, Shiv, Mowry, Ellen M., Newsome, Scott D., Prince, Jerry L., Dewey, Blake E., Carass, Aaron
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908983856463872
author Hays, Savannah P.
Zuo, Lianrui
Chaudhary, Muhammad Faizyab Ali
Bartz, Kathleen M.
Remedios, Samuel W.
Zhang, Jinwei
Zhuo, Jiachen
Bilgel, Murat
Saidha, Shiv
Mowry, Ellen M.
Newsome, Scott D.
Prince, Jerry L.
Dewey, Blake E.
Carass, Aaron
author_facet Hays, Savannah P.
Zuo, Lianrui
Chaudhary, Muhammad Faizyab Ali
Bartz, Kathleen M.
Remedios, Samuel W.
Zhang, Jinwei
Zhuo, Jiachen
Bilgel, Murat
Saidha, Shiv
Mowry, Ellen M.
Newsome, Scott D.
Prince, Jerry L.
Dewey, Blake E.
Carass, Aaron
contents Reliable harmonization of heterogeneous magnetic resonance~(MR) image datasets, especially those acquired in pragmatic clinical trials, is critical to advance multi-center neuroimaging studies and translational machine learning in healthcare. We present an enhanced and rigorously validated version of the HACA3 harmonization algorithm, which we refer to as HACA3$^+$, incorporating key methodological enhancements: (1)~an improved artifact encoder to better isolate and mitigate image artifacts, (2)~background and foreground-sensitive attention mechanisms to increase harmonization specificity, and (3)~extensive training using data spanning 100+ scanners from 64 independent sites, providing a broader diversity of scanners than other harmonization methods. Our study focuses on four commonly acquired MR image contrasts (T1-weighted, T2-weighted, proton density, \& fluid-attenuated inversion recovery), reflecting realistic clinical protocols. We perform inter-site harmonization experiments using traveling subjects to assess the generalization and robustness of the harmonization model. We compare the results of the publicly available version of HACA3 and our implementation, HACA3$^+$. Downstream relevance is further established through whole brain segmentation and image imputation. Finally, we justify each enhancement through an ablation experiment. Pre-trained weights and code for HACA3$^+$ are made publicly available at https://github.com/shays15/haca3-plus.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19474
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Harmonizing MR Images Across 100+ Scanners: Multi-site Validation with Traveling Subjects and Real-world Protocols
Hays, Savannah P.
Zuo, Lianrui
Chaudhary, Muhammad Faizyab Ali
Bartz, Kathleen M.
Remedios, Samuel W.
Zhang, Jinwei
Zhuo, Jiachen
Bilgel, Murat
Saidha, Shiv
Mowry, Ellen M.
Newsome, Scott D.
Prince, Jerry L.
Dewey, Blake E.
Carass, Aaron
Image and Video Processing
Reliable harmonization of heterogeneous magnetic resonance~(MR) image datasets, especially those acquired in pragmatic clinical trials, is critical to advance multi-center neuroimaging studies and translational machine learning in healthcare. We present an enhanced and rigorously validated version of the HACA3 harmonization algorithm, which we refer to as HACA3$^+$, incorporating key methodological enhancements: (1)~an improved artifact encoder to better isolate and mitigate image artifacts, (2)~background and foreground-sensitive attention mechanisms to increase harmonization specificity, and (3)~extensive training using data spanning 100+ scanners from 64 independent sites, providing a broader diversity of scanners than other harmonization methods. Our study focuses on four commonly acquired MR image contrasts (T1-weighted, T2-weighted, proton density, \& fluid-attenuated inversion recovery), reflecting realistic clinical protocols. We perform inter-site harmonization experiments using traveling subjects to assess the generalization and robustness of the harmonization model. We compare the results of the publicly available version of HACA3 and our implementation, HACA3$^+$. Downstream relevance is further established through whole brain segmentation and image imputation. Finally, we justify each enhancement through an ablation experiment. Pre-trained weights and code for HACA3$^+$ are made publicly available at https://github.com/shays15/haca3-plus.
title Harmonizing MR Images Across 100+ Scanners: Multi-site Validation with Traveling Subjects and Real-world Protocols
topic Image and Video Processing
url https://arxiv.org/abs/2604.19474