Cortex-Grounded Diffusion Models for Brain Image Generation

2026-01-27

AI Summary

Existing brain image synthesis methods rely on weak conditioning signals and often lack anatomical plausibility. This work proposes Cor2Vox, a novel framework that, for the first time, leverages high-resolution cortical surfaces as continuous structural priors to guide a Brownian bridge diffusion process from 3D shape to image, enabling anatomically precise and controllable brain MRI synthesis. By integrating a large-scale cortical morphometry statistical model derived from 33,000 UK Biobank subjects, Cor2Vox ensures anatomical fidelity at the sub-voxel level and supports generalization across disease phenotypes. Experiments demonstrate that Cor2Vox outperforms baseline methods in image quality, cortical reconstruction accuracy, and whole-brain segmentation metrics, with successful applications in anatomically consistent synthesis, gray matter atrophy simulation, and cross-dataset scan harmonization.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Humans and AI: Brain-Sensing and Analysis
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

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.

Problem

• brain image generation
• anatomical grounding
• cortical morphology
• synthetic neuroimaging
• biological plausibility

Innovation

• cortex-grounded diffusion
• Brownian bridge diffusion
• statistical shape model
• anatomically faithful synthesis
• cortical morphology