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

2025-11-28

AI Summary

This study addresses the challenge of bidirectional modeling and editing between pathological and healthy brain MRI scans in the absence of paired data. To this end, we propose USB—the first end-to-end unified framework for joint distribution modeling and cross-state bidirectional generation/editing of pathological and normal brain MRI. Methodologically, USB introduces a novel paired diffusion mechanism to jointly model lesions and anatomical structures, coupled with a consistency-guided strategy that preserves geometric fidelity in both anatomical topology and lesion localization during editing. Furthermore, we establish the first unified benchmark for brain image generation and editing. Extensive experiments across six public brain MRI datasets demonstrate that USB produces diverse, photorealistic images with significantly improved synthesis quality, effectively supporting downstream applications including disease detection, data augmentation, and neuroimaging analysis.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multimodal Learning
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

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.

Problem

• Generates paired pathological and healthy brain images
• Unifies bidirectional editing of brain lesions and anatomy
• Addresses lack of paired data for neuroimaging analysis

Innovation

• Unified bidirectional generation and editing framework
• Paired diffusion mechanism for joint lesion-anatomy modeling
• Consistency guidance algorithm for anatomical consistency preservation