DevelopmentODE: Structured Neural ODEs for Early Brain Development Dynamics Across a Decade

2026-09-27

AI Summary

This study addresses the challenge of long-term neurodevelopmental prediction in children, where longitudinal data are sparse, individual variability is pronounced, and age-related dynamics evolve continuously. To this end, we propose a structured continuous-time modeling framework that leverages developmental channels to organize population- and individual-level variations, constrains individual deviation velocities through shared geometric structures, and incorporates an age-dependent vector field deformation mechanism for smooth dynamic evolution. Technically, the method integrates structured Neural Ordinary Differential Equations (Neural ODEs) with nonlinear bias fields to model longitudinal fMRI data in continuous time. Experimental results demonstrate that the proposed framework significantly outperforms existing baseline models in both short-range and long-range functional connectivity prediction tasks, effectively enhancing the accuracy of developmental trajectory forecasting.

Abstract

Understanding how individual brain development unfolds over childhood requires modeling developmental trajectories from sparse longitudinal observations. Long-term neurodevelopmental forecasting is challenging because each child is typically observed at only a few irregularly spaced visits, while developmental dynamics vary across individuals and age. Generic continuous-time models accommodate irregular timing but often absorb these factors into a single flexible transition function, providing little structure for how population progression, individual variability, and developmental age shape the dynamics. We propose DevelopmentODE, a structured continuous-time framework that organizes population- and subject-specific variation within a shared developmental geometry while allowing the governing dynamics to evolve with age. The model builds this geometry around a developmental canal representing the population trajectory, whose local direction provides a reference for organizing subject-specific variation. Subject deviation velocities are constrained relative to this direction, while a shared nonlinear deviation field captures individual developmental motion without disrupting population-level progression. DevelopmentODE further models developmental non-stationarity through ordered age-dependent deformations of the shared vector field, progressively adapting a common dynamical structure as age changes, while elapsed time determines the integration horizon. This formulation uses population-level developmental structure to guide learning from sparse individual trajectories while allowing dynamics to evolve smoothly with age. We evaluate DevelopmentODE on longitudinal fMRI by predicting future functional connectivity of the same child from earlier observations. DevelopmentODE consistently outperforms competing baselines across short- and long-horizon predictions.

Problem

• brain development
• neural ODEs
• longitudinal modeling
• sparse observations
• developmental trajectories

Innovation

• Structured Neural ODEs
• Developmental Canal
• Longitudinal fMRI
• Non-stationary Dynamics
• Brain Development