GNN-Based Deep Surrogate Modeling of Knee Contact Mechanics: Generalizing Neuromuscular Control Patterns Across Subjects

TL;DR

This paper introduces a GNN-based surrogate model that accurately predicts knee contact stress distributions across different subjects by capturing neuromuscular control patterns, improving over traditional anatomical models.

Contribution

It demonstrates the ability of MeshGraphNet to generalize neuromuscular control variations in knee stress prediction, a novel approach in biomechanical modeling.

Findings

MGN achieved a correlation of 0.94 with ground truth.

Significantly reduced peak-stress prediction errors.

Captured non-local force pathways related to movement strategies.

Abstract

Background: Accumulation of abnormal contact stress is a primary biomechanical driver of acute meniscal tears and chronic osteoarthritis. While Finite Element Analysis (FEA) provides the necessary fidelity to quantify these injury-inducing loads, its high computational cost precludes clinical utility. Emerging deep surrogate models promise real-time assessment but suffer a critical blind spot: they predominantly focus on learning anatomical variations, largely overlooking the neuromuscular control patterns. These dynamic, subject-specific motor strategies fundamentally dictate potentially injurious stress distributions inside the knee. Methods: This study investigates the generalization capability of the topology-aware MeshGraphNet regarding cross-subject neuromuscular control patterns under fixed anatomical conditions. We constructed a dataset using gait data from nine subjects via an OpenSim-FEBio co-simulation platform. The MGN was compared against a structure-agnostic Node-wise MLP using a rigorous grouped 3-fold cross-validation on unseen subjects. Results: The MGN demonstrated superior fidelity, achieving a correlation of 0.94 with ground truth (vs. 0.88 for MLP). In contrast to the MLP, which exhibited the "peak shaving" defect common in deep learning, MGN significantly reduced peak-stress prediction errors and achieved higher spatial overlap in high-risk regions. This indicates that MGN effectively captured the non-local force-transmission pathways unique to each subject's movement strategy. Conclusion: By mimicking the propagation of physical stress through message passing, MGN successfully decodes the heterogeneity of human neuromuscular control, even under fixed anatomy. This establishes GNNs as robust clinical tools capable of identifying functional injury risks that are invisible to purely geometry-based surrogate models.