Controllable Surface Diffusion Generative Model for Neurodevelopmental Trajectories

2025-07-21

AI Summary

Preterm birth significantly disrupts cortical neurodevelopmental trajectories, yet individual outcomes vary widely—necessitating interpretable, subject-specific developmental modeling to identify early biomarkers. Existing generative models fail to preserve subject-specific cortical folding topology and regional morphometry. To address this, we propose a controllable graph diffusion generative framework grounded in dHCP infant cortical surface data, integrating graph-structured anatomical priors with age-conditioned control mechanisms to accurately simulate individualized cortical maturation trajectories. The model faithfully preserves topological fidelity while recapitulating region-specific developmental changes. Validation using an independent age-regression network demonstrates strong biological plausibility: predicted ages from generated surfaces achieve a mean absolute error of 0.85 ± 0.62 years. This work advances personalized neurodevelopmental modeling and holds promise for early clinical biomarker discovery.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Probabilistic Circuits and Graphical Models
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: User model development and evaluation
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Preterm birth disrupts the typical trajectory of cortical neurodevelopment, increasing the risk of cognitive and behavioral difficulties. However, outcomes vary widely, posing a significant challenge for early prediction. To address this, individualized simulation offers a promising solution by modeling subject-specific neurodevelopmental trajectories, enabling the identification of subtle deviations from normative patterns that might act as biomarkers of risk. While generative models have shown potential for simulating neurodevelopment, prior approaches often struggle to preserve subject-specific cortical folding patterns or to reproduce region-specific morphological variations. In this paper, we present a novel graph-diffusion network that supports controllable simulation of cortical maturation. Using cortical surface data from the developing Human Connectome Project (dHCP), we demonstrate that the model maintains subject-specific cortical morphology while modeling cortical maturation sufficiently well to fool an independently trained age regression network, achieving a prediction accuracy of $0.85 pm 0.62$.

Problem

• Predicting preterm infants' neurodevelopmental risks early
• Modeling subject-specific cortical maturation trajectories accurately
• Preserving individual cortical folding patterns in simulations

Innovation

• Graph-diffusion network for cortical maturation simulation
• Preserves subject-specific cortical folding patterns
• Models region-specific morphological variations accurately