2026-10-12T20:28:36Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33771982 2026-09-15T05:38:13Z category_21 portal_316 item_type_3 month_year_09_2026

Data Sheet 1_A Gyroid TPMS-based machine learning framework for rapid prediction of cancellous bone mechanical properties.zip Xinzhe Chen (24139619) Jiqing Chen (616977) Fengchong Lan (616976) Biotechnology cancellous bone machine learning mechanical properties parametric modeling TPMS Introduction<p>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.</p>Methods<p>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.</p>Results<p>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.</p>Discussion<p>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.</p> 2026-09-15T05:38:13Z Dataset Dataset 10.3389/fbioe.2026.1870920.s002 https://figshare.com/articles/dataset/Data_Sheet_1_A_Gyroid_TPMS-based_machine_learning_framework_for_rapid_prediction_of_cancellous_bone_mechanical_properties_zip/33771982 CC BY 4.0