Spatiotemporal graph neural process for reconstruction, extrapolation, and classification of cardiac trajectories

2025-09-16

AI Summary

This work addresses the challenges of reconstructing, extrapolating, and classifying cardiac motion trajectories under sparse spatiotemporal observations. We propose a spatiotemporal multi-graph modeling framework integrating Neural Ordinary Differential Equations (Neural ODEs), Graph Neural Networks (GNNs), and Neural Processes (NPs). The framework explicitly encodes anatomical structure, temporal continuity, and observation uncertainty, enabling end-to-end probabilistic modeling. It supports trajectory interpolation, long-horizon extrapolation, and disease classification from highly sparse node- and edge-level inputs. Our key innovation lies in embedding a GNN-parameterized vector field into the Neural ODE dynamics and leveraging Neural Processes for distributed, uncertainty-aware prediction and cross-subject generalization. Evaluated on the ACDC dataset, the method achieves 99% classification accuracy; on UK Biobank, it attains 67% atrial fibrillation detection sensitivity. Critically, it reconstructs and extrapolates full cardiac cycles with high fidelity using only a single observed cardiac cycle.

Technology Category

• Reasoning under Uncertainty: Graphical Models
• Machine Learning: Probabilistic Circuits and Graphical Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

We present a probabilistic framework for modeling structured spatiotemporal dynamics from sparse observations, focusing on cardiac motion. Our approach integrates neural ordinary differential equations (NODEs), graph neural networks (GNNs), and neural processes into a unified model that captures uncertainty, temporal continuity, and anatomical structure. We represent dynamic systems as spatiotemporal multiplex graphs and model their latent trajectories using a GNN-parameterized vector field. Given the sparse context observations at node and edge levels, the model infers a distribution over latent initial states and control variables, enabling both interpolation and extrapolation of trajectories. We validate the method on three synthetic dynamical systems (coupled pendulum, Lorenz attractor, and Kuramoto oscillators) and two real-world cardiac imaging datasets - ACDC (N=150) and UK Biobank (N=526) - demonstrating accurate reconstruction, extrapolation, and disease classification capabilities. The model accurately reconstructs trajectories and extrapolates future cardiac cycles from a single observed cycle. It achieves state-of-the-art results on the ACDC classification task (up to 99% accuracy), and detects atrial fibrillation in UK Biobank subjects with competitive performance (up to 67% accuracy). This work introduces a flexible approach for analyzing cardiac motion and offers a foundation for graph-based learning in structured biomedical spatiotemporal time-series data.

Problem

• Modeling cardiac motion from sparse observations
• Reconstructing and extrapolating cardiac trajectories
• Classifying cardiac diseases from motion data

Innovation

• Probabilistic framework with neural ODEs
• Graph neural networks for anatomical structure
• Neural processes for uncertainty modeling