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

TL;DR

USB is a novel end-to-end framework that unifies bidirectional generation and editing of pathological and healthy brain images, enabling realistic and diverse neuroimaging data synthesis for improved analysis.

Contribution

It introduces the first unified model for bidirectional brain image generation and editing, combining lesion and anatomy modeling with a consistency guidance algorithm.

Findings

Achieves realistic, diverse brain image generation across multiple datasets.

Demonstrates effective bidirectional editing preserving anatomical and lesion consistency.

Establishes a new benchmark for brain image synthesis and editing.

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.