EUVIMEDEUVIMED entdecken
Crossref

Modeling long-range dependencies in knee joint contact mechanics: topology diffusion, global routing, and their hybridization

Zhengye Pan, Jianwei Zuo, Jiajia Luo

Medical & Biological Engineering & Computing · 2026-10 · 64 (10) · 3881-3892

DOI: 10.1007/s11517-026-03675-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 08.09.2026. Verfasst von Zhengye Pan und 2 weiteren Autor:innen. Beteiligte Einrichtung: Biomedical Engineering Department, Institute of Advanced Clinical Medicine, Peking University, Beijing, China. Hauptthemen laut MEDLINE: Knee Joint, Models, Biological. Die Arbeit nennt 19 Literaturangaben. Gefördert von: National Key R&D Program of China, Beijing Natural Science Foundation, NSFC General Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Finite element analysis of knee joint contact mechanics is computationally expensive, which has motivated the development of graph neural network surrogate models. However, effectively representing long-range dependencies in joint mechanical responses remains challenging. Topology diffusion and global routing capture nonlocal interactions through different structural assumptions; determining whether either mechanism is sufficient, or whether they are complementary, is important for designing mechanically grounded surrogates. This study systematically compared topology diffusion, global routing, and their hybridization for surrogate modeling of knee joint contact mechanics. Using kinematic and force data from nine soccer players performing change-of-direction maneuvers, finite element simulations generated graph-structured samples for grouped three-fold cross-subject evaluation. Five architectures were compared: standard MeshGraphNet, hierarchical MeshGraphNet, a routing-only transformer, a topology-biased routing transformer, and a hybrid model. The hybrid model performed best overall, reducing RMSE by 20.0% relative to standard MeshGraphNet (0.044 ± 0.005 vs. 0.055 ± 0.008; p = 0.039), while also yielding the lowest peak stress error and the highest spatial agreement for high-risk regions. Standard MeshGraphNet was the strongest non-hybrid model, whereas routing-only strategies were less effective. These findings indicate that topology diffusion provides a robust foundation, while global routing offers complementary gains in reconstructing clinically relevant high-stress patterns. Graphical Abstract

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Knee JointModels, BiologicalHumansBiomechanical PhenomenaFinite Element AnalysisMaleGraph Neural NetworksComputer SimulationYoung AdultSoccerAdult

Stichwörter der Autor:innen

Graph neural networksKnee joint contact mechanicsLong-range dependenciesSurrogate modeling

Autor:innen und Institutionen

  • Biomedical Engineering Department, Institute of Advanced Clinical Medicine, Peking University, Beijing, China.
  • Institute of Medical Technology, Peking University Health Science Center, Peking University, Beijing, China.
  • Biomedical Engineering Department, Institute of Advanced Clinical Medicine, Peking University, Beijing, China. jiajia.luo@pku.edu.cn.
  • Institute of Medical Technology, Peking University Health Science Center, Peking University, Beijing, China. jiajia.luo@pku.edu.cn.

Förderung

  • National Key R&D Program of China
  • Beijing Natural Science Foundation
  • NSFC General Program

Zitieren

APA

Pan, Z., Zuo, J., & Luo, J. (2026). Modeling long-range dependencies in knee joint contact mechanics: topology diffusion, global routing, and their hybridization. Medical & Biological Engineering & Computing, 64(10), 3881-3892. https://doi.org/10.1007/s11517-026-03675-0

Vancouver

Pan Z, Zuo J, Luo J. Modeling long-range dependencies in knee joint contact mechanics: topology diffusion, global routing, and their hybridization. Medical & Biological Engineering & Computing. 2026;64(10):3881-3892. doi:10.1007/s11517-026-03675-0

BibTeX
@article{Pan2026,
  author = {Pan, Zhengye and Zuo, Jianwei and Luo, Jiajia},
  title = {Modeling long-range dependencies in knee joint contact mechanics: topology diffusion, global routing, and their hybridization},
  journal = {Medical & Biological Engineering & Computing},
  year = {2026},
  volume = {64},
  number = {10},
  pages = {3881--3892},
  doi = {10.1007/s11517-026-03675-0}
}
Kostenlos starten →