# ImUnity: a generalizable VAE-GAN solution for multicenter MR image harmonization

arXiv: https://arxiv.org/abs/2109.06756 · HTML: https://mlsanity.com/paper/2109.06756/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 30 references that are in the map.
- First posted on arXiv 14 Sep 2021.

## Builds on (most cited first, 5 of 5)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data](https://mlsanity.com/paper/2002.03366/) (2020)
- [Information-based Disentangled Representation Learning for Unsupervised MR Harmonization](https://mlsanity.com/paper/2103.13283/) (2021)
- [Harmonization of diffusion MRI datasets with adaptive dictionary learning](https://mlsanity.com/paper/1910.00272/) (2019)

## Built on by (most cited first, 16 of 16)

- [Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework](https://mlsanity.com/paper/2402.06875/) (2024)
- [Unpaired Volumetric Harmonization of Brain MRI with Conditional Latent Diffusion](https://mlsanity.com/paper/2408.09315/) (2024)
- [IGUANe: a 3D generalizable CycleGAN for multicenter harmonization of brain MR images](https://mlsanity.com/paper/2402.03227/) (2024)
- [Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization](https://mlsanity.com/paper/2407.15717/) (2024)
- [Diffusion based multi-domain neuroimaging harmonization method with preservation of anatomical details](https://mlsanity.com/paper/2409.00807/) (2024)
- [Structural Connectome Harmonization Using Deep Learning: The Strength of Graph Neural Networks](https://mlsanity.com/paper/2507.13992/) (2025)
- [Contrastive Anatomy-Contrast Disentanglement: A Domain-General MRI Harmonization Method](https://mlsanity.com/paper/2509.06592/) (2025)
- [IHF-Harmony: Multi-Modality Magnetic Resonance Images Harmonization using Invertible Hierarchy Flow Model](https://mlsanity.com/paper/2602.21536/) (2026)
- [SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysis](https://mlsanity.com/paper/2303.15965/) (2023)
- [Efficient and robust 3D blind harmonization for large domain gaps](https://mlsanity.com/paper/2505.00133/) (2025)
- [Flip Distribution Alignment VAE for Multi-Phase MRI Synthesis](https://mlsanity.com/paper/2510.02970/) (2025)
- [Unified Multi-Site Multi-Sequence Brain MRI Harmonization Enriched by Biomedical Semantic Style](https://mlsanity.com/paper/2601.08193/) (2026)
- [Self-Supervised Multi-Stage Domain Unlearning for White-Matter Lesion Segmentation](https://mlsanity.com/paper/2603.13328/) (2026)
- [When To Adapt? Adapting the Model or Data in Federated Medical Imaging](https://mlsanity.com/paper/2605.00892/) (2026)
- [A Target-Free Harmonization Method for MRI](https://mlsanity.com/paper/2605.01282/) (2026)
- [Task-Adaptive 3D Cross-Field MRI Translation via Field-Conditioned Content-Style Pretraining](https://mlsanity.com/paper/2608.09264/) (2026)

## Abstract (arXiv)

ImUnity is an original deep-learning model designed for efficient and flexible MR image harmonization. A VAE-GAN network, coupled with a confusion module and an optional biological preservation module, uses multiple 2D-slices taken from different anatomical locations in each subject of the training database, as well as image contrast transformations for its self-supervised training. It eventually generates 'corrected' MR images that can be used for various multi-center population studies. Using 3 open source databases (ABIDE, OASIS and SRPBS), which contain MR images from multiple acquisition scanner types or vendors and a large range of subjects ages, we show that ImUnity: (1) outperforms state-of-the-art methods in terms of quality of images generated using traveling subjects; (2) removes sites or scanner biases while improving patients classification; (3) harmonizes data coming from new sites or scanners without the need for an additional fine-tuning and (4) allows the selection of multiple MR reconstructed images according to the desired applications. Tested here on T1-weighted images, ImUnity could be used to harmonize other types of medical images.