# Unified Multi-Site Multi-Sequence Brain MRI Harmonization Enriched by Biomedical Semantic Style

arXiv: https://arxiv.org/abs/2601.08193 · HTML: https://mlsanity.com/paper/2601.08193/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 56 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models](https://mlsanity.com/paper/2308.07863/) (2023)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network](https://mlsanity.com/paper/1802.09655/) (2018)
- [GANs for Medical Image Analysis](https://mlsanity.com/paper/1809.06222/) (2018)
- [Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets](https://mlsanity.com/paper/2209.02032/) (2022)
- [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)
- [Diffusion Models for Contrast Harmonization of Magnetic Resonance Images](https://mlsanity.com/paper/2303.08189/) (2023)
- [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)
- [Denoising Diffusion Models for Inpainting of Healthy Brain Tissue](https://mlsanity.com/paper/2402.17307/) (2024)
- [Disentangling A Single MR Modality](https://mlsanity.com/paper/2205.04982/) (2022)
- [Quantitative Metrics for Benchmarking Medical Image Harmonization](https://mlsanity.com/paper/2402.04426/) (2024)
- [Harmonizing Flows: Unsupervised MR harmonization based on normalizing flows](https://mlsanity.com/paper/2301.11551/) (2023)
- [Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework](https://mlsanity.com/paper/2402.06875/) (2024)
- [A Review of Latent Representation Models in Neuroimaging](https://mlsanity.com/paper/2412.19844/) (2024)

## Abstract (arXiv)

Aggregating multi-site brain MRI data can enhance deep learning model training, but also introduces non-biological heterogeneity caused by site-specific variations (e.g., differences in scanner vendors, acquisition parameters, and imaging protocols) that can undermine generalizability. Recent retrospective MRI harmonization seeks to reduce such site effects by standardizing image style (e.g., intensity, contrast, noise patterns) while preserving anatomical content. However, existing methods often rely on limited paired traveling-subject data or fail to effectively disentangle style from anatomy. Furthermore, most current approaches address only single-sequence harmonization, restricting their use in real-world settings where multi-sequence MRI is routinely acquired. To this end, we introduce MMH, a unified framework for multi-site multi-sequence brain MRI harmonization that leverages biomedical semantic priors for sequence-aware style alignment. MMH operates in two stages: (1) a diffusion-based global harmonizer that maps MR images to a sequence-specific unified domain using style-agnostic gradient conditioning, and (2) a target-specific fine-tuner that adapts globally aligned images to desired target domains. A tri-planar attention BiomedCLIP encoder aggregates multi-view embeddings to characterize volumetric style information, allowing explicit disentanglement of image styles from anatomy without requiring paired data. Evaluations on 4,163 T1- and T2-weighted MRIs demonstrate MMH's superior harmonization over state-of-the-art methods in image feature clustering, voxel-level comparison, tissue segmentation, and downstream age and site classification.