# Harmonizing Flows: Unsupervised MR harmonization based on normalizing flows

arXiv: https://arxiv.org/abs/2301.11551 · HTML: https://mlsanity.com/paper/2301.11551/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 27 Jan 2023.

## Builds on (most cited first, 18 of 18)

- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows](https://mlsanity.com/paper/2107.12571/) (2021)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design](https://mlsanity.com/paper/1902.00275/) (2019)
- [Why Normalizing Flows Fail to Detect Out-of-Distribution Data](https://mlsanity.com/paper/2006.08545/) (2020)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [MoFlow: An Invertible Flow Model for Generating Molecular Graphs](https://mlsanity.com/paper/2006.10137/) (2020)
- [Noise Flow: Noise Modeling with Conditional Normalizing Flows](https://mlsanity.com/paper/1908.08453/) (2019)
- [Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation](https://mlsanity.com/paper/2004.04668/) (2020)
- [Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation](https://mlsanity.com/paper/2106.14999/) (2021)
- [AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows](https://mlsanity.com/paper/1905.12892/) (2019)
- [3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study](https://mlsanity.com/paper/1612.03925/) (2016)
- [Information-based Disentangled Representation Learning for Unsupervised MR Harmonization](https://mlsanity.com/paper/2103.13283/) (2021)
- [Harmonization with Flow-based Causal Inference](https://mlsanity.com/paper/2106.06845/) (2021)
- [Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment](https://mlsanity.com/paper/2003.12170/) (2020)
- [Realistic Image Normalization for Multi-Domain Segmentation](https://mlsanity.com/paper/2009.14024/) (2020)

## Built on by (most cited first, 5 of 5)

- [Fr'echet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets](https://mlsanity.com/paper/2412.01496/) (2024)
- [Unpaired Volumetric Harmonization of Brain MRI with Conditional Latent Diffusion](https://mlsanity.com/paper/2408.09315/) (2024)
- [Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization](https://mlsanity.com/paper/2407.15717/) (2024)
- [ContourDiff: Unpaired Medical Image Translation with Structural Consistency](https://mlsanity.com/paper/2403.10786/) (2024)
- [Unified Multi-Site Multi-Sequence Brain MRI Harmonization Enriched by Biomedical Semantic Style](https://mlsanity.com/paper/2601.08193/) (2026)

## Abstract (arXiv)

In this paper, we propose an unsupervised framework based on normalizing flows that harmonizes MR images to mimic the distribution of the source domain. The proposed framework consists of three steps. First, a shallow harmonizer network is trained to recover images of the source domain from their augmented versions. A normalizing flow network is then trained to learn the distribution of the source domain. Finally, at test time, a harmonizer network is modified so that the output images match the source domain's distribution learned by the normalizing flow model. Our unsupervised, source-free and task-independent approach is evaluated on cross-domain brain MRI segmentation using data from four different sites. Results demonstrate its superior performance compared to existing methods.