A novel training-free method for real-time prediction of femoral strain.
A novel training-free method for real-time prediction of femoral strain.
复制标题
DOI：
10.1016/j.jbiomech.2019.01.057
复制
发表时间：
2019-03
影响因子：
2.4
通讯作者：
H. Ziaeipoor;Mark Taylor;M. Pandy;S. Martelli
中科院分区：
文献类型：
--
作者：
H. Ziaeipoor;Mark Taylor;M. Pandy;S. Martelli
快速计算股骨应变的替代方法受到训练数据范围的限制。我们比较了一种新开发的基于叠加原理的无训练方法（superposition principle method， SPM）和流行的替代方法来计算活动期间的股骨应变。之前已经获得了五种不同活动类型的股骨劳损、肌肉和关节力的有限元计算。分别对拉丁超立方体（LH）和实验设计（DOE）抽样生成的50、100、200和300个随机样本进行多元线性回归、多元自适应样条回归和高斯过程训练。SPM方法使用173个独立于活动的有限元分析的加权线性组合，计算每个肌肉和髋关节接触力。在代理方法中，我们发现200个DOE样本始终提供低误差（RMSE < 100µε），模型构建时间为3.8 ~ 63.3 h，预测时间为6 ~ 1236 s。SPM方法的误差最小（RMSE = 40µε），模型构建时间最快（3.2 h），单活动预测时间仅次于多元线性回归（6 s），为36 s。SPM方法将使股骨应变的大量数值研究成为可能，并将缩小骨应变预测与实时临床应用之间的差距。
Surrogate methods for rapid calculation of femoral strain are limited by the scope of the training data. We compared a newly developed training-free method based on the superposition principle (Superposition Principle Method, SPM) and popular surrogate methods for calculating femoral strain during activity. Finite-element calculations of femoral strain, muscle, and joint forces for five different activity types were obtained previously. Multi-linear regression, multivariate adaptive regression splines, and Gaussian process were trained for 50, 100, 200, and 300 random samples generated using Latin Hypercube (LH) and Design of Experiment (DOE) sampling. The SPM method used weighted linear combinations of 173 activity-independent finite-element analyses accounting for each muscle and hip contact force. Across the surrogate methods, we found that 200 DOE samples consistently provided low error (RMSE < 100 µε), with model construction time ranging from 3.8 to 63.3 h and prediction time ranging from 6 to 1236 s per activity. The SPM method provided the lowest error (RMSE = 40 µε), the fastest model construction time (3.2 h) and the second fastest prediction time per activity (36 s) after Multi-linear Regression (6 s). The SPM method will enable large numerical studies of femoral strain and will narrow the gap between bone strain prediction and real-time clinical applications.