Frontiers in bioengineering and biotechnology · 2026
A Gyroid TPMS-based machine learning framework for rapid prediction of cancellous bone mechanical properties.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Chen Xinzhe, Chen Jiqing, Lan Fengchong
Аннотация
INTRODUCTION: High-fidelity finite-element analysis of cancellous bone is computationally expensive, particularly when large parameter spaces must be explored. This study developed a rapid surrogate-modeling framework integrating parametric Gyroid modeling, finite-element analysis, and machine learning to predict the apparent mechanical properties of cancellous-bone models.
METHODS: Trabecular tissue Young's modulus (E t), tissue failure strain (ε t), bone volume fraction (BV/TV), and degree of anisotropy (DA) were used as inputs. A database of 200 parameter combinations was generated using Latin hypercube sampling, with apparent Young's modulus (E c) and failure stress (σ c) obtained from finite-element simulations as separate outputs. Multiple linear regression, quadratic polynomial regression, support vector regression, Kriging, and a backpropagation neural network were evaluated using nested five-fold cross-validation.
RESULTS: The finite-element model reproduced published uniaxial compression responses. BPNN achieved the best prediction of E c (R2 = 0.9993 ± 0.0003, NRMSE = 0.0256 ± 0.0027, MAPE = 1.68 ± 0.38%), whereas SVR performed best for σ c (R2 = 0.9987 ± 0.0004, NRMSE = 0.0352 ± 0.0030, MAPE = 2.23 ± 0.45%). Response-surface analysis showed that E t and BV/TV primarily governed apparent stiffness, while failure stress was additionally sensitive to ε t.
DISCUSSION: The proposed framework provides an accurate and computationally efficient approach for rapid prediction, parameter screening, response-surface analysis, and structural design exploration within the investigated Gyroid model space.
METHODS: Trabecular tissue Young's modulus (E t), tissue failure strain (ε t), bone volume fraction (BV/TV), and degree of anisotropy (DA) were used as inputs. A database of 200 parameter combinations was generated using Latin hypercube sampling, with apparent Young's modulus (E c) and failure stress (σ c) obtained from finite-element simulations as separate outputs. Multiple linear regression, quadratic polynomial regression, support vector regression, Kriging, and a backpropagation neural network were evaluated using nested five-fold cross-validation.
RESULTS: The finite-element model reproduced published uniaxial compression responses. BPNN achieved the best prediction of E c (R2 = 0.9993 ± 0.0003, NRMSE = 0.0256 ± 0.0027, MAPE = 1.68 ± 0.38%), whereas SVR performed best for σ c (R2 = 0.9987 ± 0.0004, NRMSE = 0.0352 ± 0.0030, MAPE = 2.23 ± 0.45%). Response-surface analysis showed that E t and BV/TV primarily governed apparent stiffness, while failure stress was additionally sensitive to ε t.
DISCUSSION: The proposed framework provides an accurate and computationally efficient approach for rapid prediction, parameter screening, response-surface analysis, and structural design exploration within the investigated Gyroid model space.