Evaluating Deep Surrogate Models for Knee Joint Contact Mechanics Under Input-Limited Conditions

TL;DR

This study compares various surrogate models for knee joint contact mechanics, emphasizing their robustness under input-limited conditions and highlighting the importance of preserving risk-relevant information in practical scenarios.

Contribution

It introduces a comprehensive evaluation framework for surrogate models under realistic input constraints, revealing the hybrid model's robustness and task-dependent optimality.

Findings

Hybrid model performed best with full inputs and under corrupted conditions.

No single model dominated under minimal inputs; performance varied by metric.

Evaluation should focus on risk-relevant information preservation, not just accuracy.

Abstract

Background and Objective: Accurate surrogate modeling of knee joint contact mechanics is important for reconstructing stress distributions and identifying risk-relevant regions, yet the relative suitability of different modeling paradigms under practically relevant input-limited conditions remains unclear. Methods: Nine male soccer players performed 90{\deg} change-of-direction trials. Finite element simulations driven by subject-specific joint posture and reaction forces were converted into graph-structured samples. Five surrogate architectures representing local diffusion, history-context enhancement, hierarchical multi-scale modeling, explicit global interaction, and local-global hybridization were compared using three-fold cross-subject validation under full, pose-corrupted, load-corrupted, and minimal-input conditions. Performance was evaluated using full-field error, high-stress error, high-risk region overlap, and hotspot localization metrics. Results: The hybrid model achieved the best overall performance under full inputs and remained the most robust under pose- and load-corrupted conditions. Under minimal inputs, no single model dominated all metrics: the history-context model yielded lower overall and high-stress errors, the hybrid model better preserved high-risk region reconstruction, and the hierarchical model showed an advantage in hotspot localization. Conclusion: Evaluation of surrogate models for knee joint contact mechanics should shift from accuracy comparisons under ideal inputs to a comprehensive assessment of the preservation of risk-relevant information under realistic input constraints. Although the local-global hybrid model showed the best overall robustness, the optimal model under minimal-input conditions remained task-dependent.