Automated personalization of biomechanical knee model

被引:1
作者
Yurova, Alexandra [1 ]
Lychagin, Alexey [2 ]
Kalinsky, Eugene [2 ]
Vassilevski, Yuri [1 ,2 ,3 ]
Elizarov, Mikhail [2 ]
Garkavi, Andrey [2 ]
机构
[1] Russian Acad Sci, Marchuk Inst Numer Math, 8 Gubkin Str, Moscow 119333, Russia
[2] Sechenov Univ, 8-2 Trubetskaya str, Moscow 119991, Russia
[3] Sirius Univ, Ctr IT &AI, 1 Olympiyskii pr, Soci 354340, Russia
基金
俄罗斯科学基金会;
关键词
Lateral patellar compression syndrome; Knee joint; Knee CT segmentation; U-Net; Machine learning; Biomechanical knee model; Patellofemoral joint; PATELLOFEMORAL PAIN; KINEMATICS; PATHOMECHANICS; INDIVIDUALS; JOINT;
D O I
10.1007/s11548-024-03075-5
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
PurposePatient-specific biomechanical models of the knee joint can effectively aid in understanding the reasons for pathologies and improve diagnostic methods and treatment procedures. For deeper research of knee diseases, the development of biomechanical models with appropriate configurations is essential. In this study, we mainly focus on the development of a personalized biomechanical model for the investigation of knee joint pathologies related to patellar motion using automated methods.MethodsThis study presents a biomechanical model created for patellar motion pathologies research and some techniques for automating the generation of the biomechanical model. To generate geometric models of bones, the U-Net neural network was adapted for 3D input datasets. The method uses the same neural network for segmentation of femur, tibia, patella and fibula. The total size of the train/validation (75/25%) dataset is 18,183 3D volumes of size 512x512x4\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$512\times 512\times 4$$\end{document} voxels. The configuration of the biomechanical knee model proposed in the paper includes six degrees of freedom for the tibiofemoral and patellofemoral joints, lateral and medial contact surfaces for femur and tibia, and ligaments, representing, among other things, the medial and lateral stabilizers of the knee cap. The development of the personalized biomechanical model was carried out using the OpenSim software system. The automated model generation was implemented using OpenSim Python scripting commands.ResultsThe neural network for bones segmentation achieves mean DICE 0.9838. A biomechanical model for realistic simulation of patellar movement within the trochlear groove was proposed. Generation of personalized biomechanical models was automated.ConclusionsIn this paper, we have implemented a neural network for the segmentation of 3D CT scans of the knee joint to produce a biomechanical model for the study of knee cap motion pathologies. Most stages of the generation process have been automated and can be used to generate patient-specific models.
引用
收藏
页码:891 / 902
页数:12
相关论文
共 40 条
[1]  
Al-Hakim Wisam, 2012, Open Orthop J, V6, P320, DOI 10.2174/1874325001206010320
[2]   Patellofemoral kinematics during knee flexion-extension: An in vitro study [J].
Amis, Andrew A. ;
Senavongse, Wongwit ;
Bull, Anthony M. J. .
JOURNAL OF ORTHOPAEDIC RESEARCH, 2006, 24 (12) :2201-2211
[3]  
Anderson FRANK C., 1999, Comput Methods Biomech Biomed Engin, V2, P201, DOI 10.1080/10255849908907988
[4]   Greater peak rearfoot eversion predicts foot orthoses efficacy in individuals with patellofemoral pain syndrome [J].
Barton, C. J. ;
Menz, H. B. ;
Levinger, P. ;
Webster, K. E. ;
Crossley, K. M. .
BRITISH JOURNAL OF SPORTS MEDICINE, 2011, 45 (09) :697-701
[5]  
Blond L, 1998, Acta Orthop Belg, V64, P393
[6]   Gender differences in the incidence and prevalence of patellofemoral pain syndrome [J].
Boling, M. ;
Padua, D. ;
Marshall, S. ;
Guskiewicz, K. ;
Pyne, S. ;
Beutler, A. .
SCANDINAVIAN JOURNAL OF MEDICINE & SCIENCE IN SPORTS, 2010, 20 (05) :725-730
[7]   CT- and MRI-Based 3D Reconstruction of Knee Joint to Assess Cartilage and Bone [J].
Ciliberti, Federica Kiyomi ;
Guerrini, Lorena ;
Gunnarsson, Arnar Evgeni ;
Recenti, Marco ;
Jacob, Deborah ;
Cangiano, Vincenzo ;
Tesfahunegn, Yonatan Afework ;
Islind, Anna Sigriour ;
Tortorella, Francesco ;
Tsirilaki, Mariella ;
Jonsson Jr, Halldor ;
Gargiulo, Paolo ;
Aubonnet, Romain .
DIAGNOSTICS, 2022, 12 (02)
[8]   Quality of life in individuals with patellofemoral pain: A systematic review including meta-analysis [J].
Coburn, Sally L. ;
Barton, Christian J. ;
Filbay, Stephanie R. ;
Hart, Harvi F. ;
Rathleff, Michael S. ;
Crossley, Kay M. .
PHYSICAL THERAPY IN SPORT, 2018, 33 :96-108
[9]   OpenSim: open-source software to create and analyze dynamic Simulations of movement [J].
Delp, Scott L. ;
Anderson, Frank C. ;
Arnold, Allison S. ;
Loan, Peter ;
Habib, Ayman ;
John, Chand T. ;
Guendelman, Eran ;
Thelen, Darryl G. .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2007, 54 (11) :1940-1950
[10]   AN INTERACTIVE GRAPHICS-BASED MODEL OF THE LOWER-EXTREMITY TO STUDY ORTHOPEDIC SURGICAL-PROCEDURES [J].
DELP, SL ;
LOAN, JP ;
HOY, MG ;
ZAJAC, FE ;
TOPP, EL ;
ROSEN, JM .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1990, 37 (08) :757-767