A Cycle-Consistent Graph Surrogate for Full-Cycle Left Ventricular Myocardial Biomechanics

2026-02-06

AI Summary

Traditional finite element methods for simulating left ventricular myocardial biomechanics are computationally expensive, while existing graph-based surrogate models struggle to predict the full cardiac cycle, and physics-informed neural networks face convergence difficulties on complex cardiac geometries. To address these challenges, this work proposes CGFENet, a unified graph surrogate model that integrates a global–local graph encoder, a volume–time-driven recurrent temporal encoder, and a bidirectional loading/unloading consistent framework for full-cycle modeling. By synergistically combining graph neural networks, gated recurrent units, a weak-form-inspired global coupling mechanism, and a lumped-parameter model, CGFENet substantially reduces reliance on finite element supervision data. It achieves high-fidelity predictions with significantly less training data while generating physiologically plausible pressure–volume loops.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Image-based patient-specific simulation of left ventricular (LV) mechanics is valuable for understanding cardiac function and supporting clinical intervention planning, but conventional finite-element analysis (FEA) is computationally intensive. Current graph-based surrogates do not have full-cycle prediction capabilities, and physics-informed neural networks often struggle to converge on complex cardiac geometries. We present CardioGraphFENet (CGFENet), a unified graph-based surrogate for rapid full-cycle estimation of LV myocardial biomechanics, supervised by a large FEA simulation dataset. The proposed model integrates (i) a global--local graph encoder to capture mesh features with weak-form-inspired global coupling, (ii) a gated recurrent unit-based temporal encoder conditioned on the target volume-time signal to model cycle-coherent dynamics, and (iii) a cycle-consistent bidirectional formulation for both loading and inverse unloading within a single framework. These strategies enable high fidelity with respect to traditional FEA ground truths and produce physiologically plausible pressure-volume loops that match FEA results when coupled with a lumped-parameter model. In particular, the cycle-consistency strategy enables a significant reduction in FEA supervision with only minimal loss in accuracy.

Problem

• left ventricular biomechanics
• full-cycle simulation
• graph surrogate
• computational efficiency
• cycle consistency

Innovation

• graph neural network
• cycle-consistent modeling
• biomechanics surrogate
• left ventricular mechanics
• physics-informed learning