# Harmonization of breast MRI data

> **NIH NIH R01** · DUKE UNIVERSITY · 2022 · $657,101

## Abstract

ABSTRACT
Different magnetic resonance imaging (MRI) scanners and different acquisition parameters can produce very
different images for the same patients. This is a significant issue when attempting to use MRIs in a quantitative
manner. Multiple studies have shown promise of quantitative analysis of breast MRIs to diagnose breast
tumors, predict patient outcomes, assess cancer risk, and even identify genomic signatures of cancers.
However, the issue of inhomogeneity of images hampers the progress of the research and clinical
implementation of these findings. In many cases one cannot utilize images from different sources to answer a
research question. Furthermore, predictive models developed at one institution may not generalize to other
institutions. While this is a well-recognized problem, there is currently no solution to it in breast MRI. Some
valid efforts have been undertaken in order to address this issue for other organs, predominantly brain.
However, the problem has not been solved for those organs neither and limited validation of the existing
methods in practical contexts hampers the implementation. Breast is a non-rigid organ with highly variable
composition making the harmonization of breast MRIs particularly challenging and making almost all prior
harmonization methods developed for brain not applicable. Given the urgent need for harmonization in
quantitative research, we propose three harmonization methods that allow for transforming an image acquired
using one scanner setup to assume appearance of another scanner setup. We introduce important technical
innovations to utilize cutting-edge convolutional neural networks for this task. Additionally, we propose a new
approach to the question that has not yet attracted significant systematic consideration: what makes a
harmonization algorithm successful or useful? We do not evaluate pixel-to-pixel match between the
harmonized image and a reference image which is the typical approach. This approach is impractical in breast
imaging since it requires ideally paired images, it does not deal well with expected image noise, and it does not
inform about specific limitations of the evaluated harmonization method. We propose an evaluation framework
that assesses harmonization algorithms in terms of different practical applications including radiomic analysis
and deep learning. The study will be conducted in collaboration between a machine learning scientists (Duke
and Yale), a breast MRI physicist (Cornell), a radiologist whose research focuses on MRI (Duke), and a
biostatistician (Duke). The proposed harmonization and evaluation methods do not require fully paired data
and do not make assumptions about tissue composition. Therefore, they will be applicable across other organs
once implemented with appropriate data for the organ. All harmonization and evaluation algorithms along with
the data will be made publicly available to spearhead further research on this crucial unsolved research topic.

## Key facts

- **NIH application ID:** 10367288
- **Project number:** 1R01EB031575-01A1
- **Recipient organization:** DUKE UNIVERSITY
- **Principal Investigator:** Maciej A. Mazurowski
- **Activity code:** R01 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2022
- **Award amount:** $657,101
- **Award type:** 1
- **Project period:** 2022-09-15 → 2026-06-30

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10367288

## Citation

> US National Institutes of Health, RePORTER application 10367288, Harmonization of breast MRI data (1R01EB031575-01A1). Retrieved via AI Analytics 2026-05-22 from https://api.ai-analytics.org/grant/nih/10367288. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*