# Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework

arXiv: https://arxiv.org/abs/2402.06875 · HTML: https://mlsanity.com/paper/2402.06875/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 54 references that are in the map.
- First posted on arXiv 10 Feb 2024.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1802.01221/) (2018)
- [Learning Latent Space Energy-Based Prior Model](https://mlsanity.com/paper/2006.08205/) (2020)
- [VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models](https://mlsanity.com/paper/2010.00654/) (2020)
- [Detect and Correct Bias in Multi-Site Neuroimaging Datasets](https://mlsanity.com/paper/2002.05049/) (2020)
- [Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects](https://mlsanity.com/paper/1910.04597/) (2019)
- [Multi-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge](https://mlsanity.com/paper/2007.02096/) (2020)
- [HACA3: A Unified Approach for Multi-site MR Image Harmonization](https://mlsanity.com/paper/2212.06065/) (2022)
- [ImUnity: a generalizable VAE-GAN solution for multicenter MR image harmonization](https://mlsanity.com/paper/2109.06756/) (2021)
- [Unpaired Image-to-Image Translation via Latent Energy Transport](https://mlsanity.com/paper/2012.00649/) (2020)
- [Disentangling A Single MR Modality](https://mlsanity.com/paper/2205.04982/) (2022)
- [DomainATM: Domain Adaptation Toolbox for Medical Data Analysis](https://mlsanity.com/paper/2209.11890/) (2022)

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

- [A Review of Latent Representation Models in Neuroimaging](https://mlsanity.com/paper/2412.19844/) (2024)
- [Iterative Learning for Joint Image Denoising and Motion Artifact Correction of 3D Brain MRI](https://mlsanity.com/paper/2403.08162/) (2024)
- [MeDUET: Disentangled Unified Pretraining for 3D Medical Image Synthesis and Analysis](https://mlsanity.com/paper/2602.17901/) (2026)
- [Unified Multi-Site Multi-Sequence Brain MRI Harmonization Enriched by Biomedical Semantic Style](https://mlsanity.com/paper/2601.08193/) (2026)
- [Frozen Site-Probe Accuracy Is Not a Standalone Harmonization Score: An Audit of Evaluation Practice for Multi-Site MRI](https://mlsanity.com/paper/2610.14140/) (2026)

## Abstract (arXiv)

Brain magnetic resonance imaging (MRI) has been extensively employed across clinical and research fields, but often exhibits sensitivity to site effects arising from non-biological variations such as differences in field strength and scanner vendors. Numerous retrospective MRI harmonization techniques have demonstrated encouraging outcomes in reducing the site effects at the image level. However, existing methods generally suffer from high computational requirements and limited generalizability, restricting their applicability to unseen MRIs. In this paper, we design a novel disentangled latent energy-based style translation (DLEST) framework for unpaired image-level MRI harmonization, consisting of (a) site-invariant image generation (SIG), (b) site-specific style translation (SST), and (c) site-specific MRI synthesis (SMS). Specifically, the SIG employs a latent autoencoder to encode MRIs into a low-dimensional latent space and reconstruct MRIs from latent codes. The SST utilizes an energy-based model to comprehend the global latent distribution of a target domain and translate source latent codes toward the target domain, while SMS enables MRI synthesis with a target-specific style. By disentangling image generation and style translation in latent space, the DLEST can achieve efficient style translation. Our model was trained on T1-weighted MRIs from a public dataset (with 3,984 subjects across 58 acquisition sites/settings) and validated on an independent dataset (with 9 traveling subjects scanned in 11 sites/settings) in four tasks: histogram and feature visualization, site classification, brain tissue segmentation, and site-specific structural MRI synthesis. Qualitative and quantitative results demonstrate the superiority of our method over several state-of-the-arts.