Knee-Loading Predictions with Neural Networks Improve Finite Element Modeling Classifications of Knee Osteoarthritis: Data from the Osteoarthritis Initiative
Annals of Biomedical Engineering · 2024-09 · 52 (9) · 2569-2583
DOI: 10.1007/s10439-024-03549-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Annals of Biomedical Engineering, online erschienen am 06.06.2024. Verfasst von Alexander Paz und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Technical Physics, University of Eastern Finland, Yliopistonranta 1, 70211, Kuopio, Finland. alexander.paz@uef.fi. Hauptthemen laut MEDLINE: Osteoarthritis, Knee, Finite Element Analysis, Neural Networks, Computer, Knee Joint. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Council of Finland, Sigrid Juséliuksen Säätiö, Pohjois-Savon Rahasto.
Abstract (Originalsprache)
Physics-based modeling methods have the potential to investigate the mechanical factors associated with knee osteoarthritis (OA) and predict the future radiographic condition of the joint. However, it remains unclear what level of detail is optimal in these methods to achieve accurate prediction results in cohort studies. In this work, we extended a template-based finite element (FE) method to include the lateral and medial compartments of the tibiofemoral joint and simulated the mechanical responses of 97 knees under three conditions of gait loading. Furthermore, the effects of variations in cartilage thickness and failure equation on predicted cartilage degeneration were investigated. Our results showed that using neural network-based estimations of peak knee loading provided classification performances of 0.70 (AUC, p < 0.05) in distinguishing between knees that developed severe OA or mild OA and knees that did not develop OA eight years after a healthy radiographic baseline. However, FE models incorporating subject-specific femoral and tibial cartilage thickness did not improve this classification performance, suggesting there exists an optimal point between personalized loading and geometry for discrimination purposes. In summary, we proposed a modeling framework that streamlines the rapid generation of individualized knee models achieving promising classification performance while avoiding motion capture and cartilage image segmentation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Technical Physics, University of Eastern Finland, Yliopistonranta 1, 70211, Kuopio, Finland. alexander.paz@uef.fi.
- Escuela de Ingeniería Civil y Geomática, Universidad del Valle, Cali, Colombia. alexander.paz@uef.fi.
- Department of Technical Physics, University of Eastern Finland, Yliopistonranta 1, 70211, Kuopio, Finland.
- Diagnostic Imaging Center, Wellbeing Services County of North Savo, Kuopio, Finland.
- Science Service Center, Kuopio University Hospital, Wellbeing Services County of North Savo, Kuopio, Finland.
- Escuela de Ingeniería Civil y Geomática, Universidad del Valle, Cali, Colombia.
ORCID-Profile: Rami K Korhonen
Förderung
- Research Council of Finland
- Sigrid Juséliuksen Säätiö
- Pohjois-Savon Rahasto
- Doctoral Programme in Science, Forestry, and Technology, University of Eastern Finland
- University of Eastern Finland
Zitieren
APA
Paz, A., Lavikainen, J., Turunen, M. J., García, J. J., Korhonen, R. K., & Mononen, M. E. (2024). Knee-Loading Predictions with Neural Networks Improve Finite Element Modeling Classifications of Knee Osteoarthritis: Data from the Osteoarthritis Initiative. Annals of Biomedical Engineering, 52(9), 2569-2583. https://doi.org/10.1007/s10439-024-03549-2
Vancouver
Paz A, Lavikainen J, Turunen MJ, García JJ, Korhonen RK, Mononen ME. Knee-Loading Predictions with Neural Networks Improve Finite Element Modeling Classifications of Knee Osteoarthritis: Data from the Osteoarthritis Initiative. Annals of Biomedical Engineering. 2024;52(9):2569-2583. doi:10.1007/s10439-024-03549-2
BibTeX
@article{Paz2024,
author = {Paz, Alexander and Lavikainen, Jere and Turunen, Mikael J and García, José J and Korhonen, Rami K and Mononen, Mika E},
title = {Knee-Loading Predictions with Neural Networks Improve Finite Element Modeling Classifications of Knee Osteoarthritis: Data from the Osteoarthritis Initiative},
journal = {Annals of Biomedical Engineering},
year = {2024},
volume = {52},
number = {9},
pages = {2569--2583},
doi = {10.1007/s10439-024-03549-2}
}
EUVIMED