# USB: Unified Synthetic Brain Framework for Bidirectional Pathology-Healthy Generation and Editing

arXiv: https://arxiv.org/abs/2512.00269 · HTML: https://mlsanity.com/paper/2512.00269/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 47 references that are in the map.
- First posted on arXiv 29 Nov 2025.

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

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Improving Diffusion Models for Inverse Problems using Manifold Constraints](https://mlsanity.com/paper/2206.00941/) (2022)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem](https://mlsanity.com/paper/2206.04119/) (2022)
- [SynthStrip: Skull-Stripping for Any Brain Image](https://mlsanity.com/paper/2203.09974/) (2022)
- [ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset](https://mlsanity.com/paper/2206.06694/) (2022)
- [MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion](https://mlsanity.com/paper/2203.12621/) (2022)
- [Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstruction](https://mlsanity.com/paper/2203.03623/) (2022)
- [Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN](https://mlsanity.com/paper/2008.01910/) (2020)
- [Towards performant and reliable undersampled MR reconstruction via diffusion model sampling](https://mlsanity.com/paper/2203.04292/) (2022)
- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models](https://mlsanity.com/paper/2302.03018/) (2023)
- [Can segmentation models be trained with fully synthetically generated data?](https://mlsanity.com/paper/2209.08256/) (2022)
- [3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images](https://mlsanity.com/paper/2107.09700/) (2021)
- [DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification](https://mlsanity.com/paper/2303.10610/) (2023)
- [LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models](https://mlsanity.com/paper/2403.14066/) (2024)
- [Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data](https://mlsanity.com/paper/2510.14831/) (2025)
- [Brain-ID: Learning Contrast-agnostic Anatomical Representations for Brain Imaging](https://mlsanity.com/paper/2311.16914/) (2023)
- [PEPSI: Pathology-Enhanced Pulse-Sequence-Invariant Representations for Brain MRI](https://mlsanity.com/paper/2403.06227/) (2024)
- [Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis](https://mlsanity.com/paper/2406.03002/) (2024)
- [Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomization](https://mlsanity.com/paper/2506.10233/) (2025)
- [Unraveling Normal Anatomy via Fluid-Driven Anomaly Randomization](https://mlsanity.com/paper/2501.13370/) (2025)
- [End-to-end autoencoding architecture for the simultaneous generation of medical images and corresponding segmentation masks](https://mlsanity.com/paper/2311.10472/) (2023)

## Built on by (most cited first, 1 of 1)

- [Physics-Grounded Disentangled Flow Modeling for Brain Disease Progression Trajectory](https://mlsanity.com/paper/2606.28630/) (2026)

## Abstract (arXiv)

Understanding the relationship between pathological and healthy brain structures is fundamental to neuroimaging, connecting disease diagnosis and detection with modeling, prediction, and treatment planning. However, paired pathological-healthy data are extremely difficult to obtain, as they rely on pre- and post-treatment imaging, constrained by clinical outcomes and longitudinal data availability. Consequently, most existing brain image generation and editing methods focus on visual quality yet remain domain-specific, treating pathological and healthy image modeling independently. We introduce USB (Unified Synthetic Brain), the first end-to-end framework that unifies bidirectional generation and editing of pathological and healthy brain images. USB models the joint distribution of lesions and brain anatomy through a paired diffusion mechanism and achieves both pathological and healthy image generation. A consistency guidance algorithm further preserves anatomical consistency and lesion correspondence during bidirectional pathology-healthy editing. Extensive experiments on six public brain MRI datasets including healthy controls, stroke, and Alzheimer's patients, demonstrate USB's ability to produce diverse and realistic results. By establishing the first unified benchmark for brain image generation and editing, USB opens opportunities for scalable dataset creation and robust neuroimaging analysis. Code is available at https://github.com/jhuldr/USB.