# HACA3: A Unified Approach for Multi-site MR Image Harmonization arXiv: https://arxiv.org/abs/2212.06065 ยท HTML: https://mlsanity.com/paper/2212.06065/ ## Key facts - Cited by 18 papers in the map (data through 14 Oct 2026). - Builds on 17 of its 57 references that are in the map. - First posted on arXiv 12 Dec 2022. ## Builds on (most cited first, 17 of 17) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015) - [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018) - [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018) - [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020) - [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017) - [On Disentangled Representations Learned From Correlated Data](https://mlsanity.com/paper/2006.07886/) (2020) - [Disentangled Representation Learning in Cardiac Image Analysis](https://mlsanity.com/paper/1903.09467/) (2019) - [A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation](https://mlsanity.com/paper/1809.01361/) (2018) - [3D Whole Brain Segmentation using Spatially Localized Atlas Network Tiles](https://mlsanity.com/paper/1903.12152/) (2019) - [One Model to Synthesize Them All: Multi-contrast Multi-scale Transformer for Missing Data Imputation](https://mlsanity.com/paper/2204.13738/) (2022) - [Unpaired Brain MR-to-CT Synthesis using a Structure-Constrained CycleGAN](https://mlsanity.com/paper/1809.04536/) (2018) - [Evaluating the Impact of Intensity Normalization on MR Image Synthesis](https://mlsanity.com/paper/1812.04652/) (2018) - [Representation Disentanglement for Multi-modal brain MR Analysis](https://mlsanity.com/paper/2102.11456/) (2021) - [Self domain adapted network](https://mlsanity.com/paper/2007.03162/) (2020) - [Information-based Disentangled Representation Learning for Unsupervised MR Harmonization](https://mlsanity.com/paper/2103.13283/) (2021) - [Disentangling A Single MR Modality](https://mlsanity.com/paper/2205.04982/) (2022) ## Built on by (most cited first, 18 of 18) - [Towards an accurate and generalizable multiple sclerosis lesion segmentation model using self-ensembled lesion fusion](https://mlsanity.com/paper/2312.01460/) (2023) - [Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework](https://mlsanity.com/paper/2402.06875/) (2024) - [Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization](https://mlsanity.com/paper/2407.15717/) (2024) - [MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations](https://mlsanity.com/paper/2507.00043/) (2025) - [WFM: 3D Wavelet Flow Matching for Ultrafast Multi-Modal MRI Synthesis](https://mlsanity.com/paper/2604.21146/) (2026) - [AniRes2D: Anisotropic Residual-enhanced Diffusion for 2D MR Super-Resolution](https://mlsanity.com/paper/2312.04385/) (2023) - [UNISELF: A Unified Network with Instance Normalization and Self-Ensembled Lesion Fusion for Multiple Sclerosis Lesion Segmentation](https://mlsanity.com/paper/2508.03982/) (2025) - [PRISM: Privacy-preserving Inter-Site MRI Harmonization via Disentangled Representation Learning](https://mlsanity.com/paper/2411.06513/) (2024) - [Contrastive Anatomy-Contrast Disentanglement: A Domain-General MRI Harmonization Method](https://mlsanity.com/paper/2509.06592/) (2025) - [MSRepaint: Multiple Sclerosis Repaint with Conditional Denoising Diffusion Implicit Model for Bidirectional Lesion Filling and Synthesis](https://mlsanity.com/paper/2510.02063/) (2025) - [An Artifact-based Agent Framework for Adaptive and Reproducible Medical Image Processing](https://mlsanity.com/paper/2604.21936/) (2026) - [Beyond the Lungs: Extending the Field of View in Chest CT with Latent Diffusion Models](https://mlsanity.com/paper/2501.13068/) (2025) - [Surrogate Supervision for Robust and Generalizable Deformable Image Registration](https://mlsanity.com/paper/2509.09869/) (2025) - [Unified Multi-Site Multi-Sequence Brain MRI Harmonization Enriched by Biomedical Semantic Style](https://mlsanity.com/paper/2601.08193/) (2026) - [SA-CycleGAN-2.5D: Self-Attention CycleGAN with Tri-Planar Context for Multi-Site MRI Harmonization](https://mlsanity.com/paper/2603.17219/) (2026) - [Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling](https://mlsanity.com/paper/2605.13933/) (2026) - [Recover Semantics First, Generate Better: Improved Latent Modeling for 3D MRI Reconstruction and Cross-Contrast Synthesis](https://mlsanity.com/paper/2606.17989/) (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) The lack of standardization is a prominent issue in magnetic resonance (MR) imaging. This often causes undesired contrast variations in the acquired images due to differences in hardware and acquisition parameters. In recent years, image synthesis-based MR harmonization with disentanglement has been proposed to compensate for the undesired contrast variations. Despite the success of existing methods, we argue that three major improvements can be made. First, most existing methods are built upon the assumption that multi-contrast MR images of the same subject share the same anatomy. This assumption is questionable, since different MR contrasts are specialized to highlight different anatomical features. Second, these methods often require a fixed set of MR contrasts for training (e.g., both T1-weighted and T2-weighted images), limiting their applicability. Lastly, existing methods are generally sensitive to imaging artifacts. In this paper, we present Harmonization with Attention-based Contrast, Anatomy, and Artifact Awareness (HACA3), a novel approach to address these three issues. HACA3 incorporates an anatomy fusion module that accounts for the inherent anatomical differences between MR contrasts. Furthermore, HACA3 is also robust to imaging artifacts and can be trained and applied to any set of MR contrasts. HACA3 is developed and evaluated on diverse MR datasets acquired from 21 sites with varying field strengths, scanner platforms, and acquisition protocols. Experiments show that HACA3 achieves state-of-the-art performance under multiple image quality metrics. We also demonstrate the applicability and versatility of HACA3 on downstream tasks including white matter lesion segmentation and longitudinal volumetric analyses.