Cortex-Grounded Diffusion Models for Brain Image Generation
This work addresses the scarcity and domain shift issues in real-world neuroimaging datasets for researchers and clinicians, offering a method for generating biologically plausible brain images, though it is incremental as it builds on existing diffusion models with a novel conditioning approach.
The paper tackled the problem of generating synthetic neuroimaging data by introducing Cor2Vox, a cortex-grounded generative framework that uses cortical surfaces to guide a 3D shape-to-image diffusion process, resulting in topologically faithful brain MRI synthesis with precise anatomical control and outperforming baseline methods in validation metrics.
Synthetic neuroimaging data can mitigate critical limitations of real-world datasets, including the scarcity of rare phenotypes, domain shifts across scanners, and insufficient longitudinal coverage. However, existing generative models largely rely on weak conditioning signals, such as labels or text, which lack anatomical grounding and often produce biologically implausible outputs. To this end, we introduce Cor2Vox, a cortex-grounded generative framework for brain magnetic resonance image (MRI) synthesis that ties image generation to continuous structural priors of the cerebral cortex. It leverages high-resolution cortical surfaces to guide a 3D shape-to-image Brownian bridge diffusion process, enabling topologically faithful synthesis and precise control over underlying anatomies. To support the generation of new, realistic brain shapes, we developed a large-scale statistical shape model of cortical morphology derived from over 33,000 UK Biobank scans. We validated the fidelity of Cor2Vox based on traditional image quality metrics, advanced cortical surface reconstruction, and whole-brain segmentation quality, outperforming many baseline methods. Across three applications, namely (i) anatomically consistent synthesis, (ii) simulation of progressive gray matter atrophy, and (iii) harmonization of in-house frontotemporal dementia scans with public datasets, Cor2Vox preserved fine-grained cortical morphology at the sub-voxel level, exhibiting remarkable robustness to variations in cortical geometry and disease phenotype without retraining.