{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T06:04:43Z","timestamp":1789452283041,"version":"build-2803163510"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioeng. Biotechnol."],"abstract":"\n Introduction<\/jats:title>\n 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.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n Trabecular tissue Young\u2019s modulus (\n E<\/jats:italic>\n t<\/jats:sub>\n ), tissue failure strain (\n \u03b5<\/jats:italic>\n t<\/jats:sub>\n ), bone volume fraction (\n BV\/TV<\/jats:italic>\n ), and degree of anisotropy (\n DA<\/jats:italic>\n ) were used as inputs. A database of 200 parameter combinations was generated using Latin hypercube sampling, with apparent Young\u2019s modulus (\n E<\/jats:italic>\n c<\/jats:sub>\n ) and failure stress (\n \u03c3<\/jats:italic>\n c<\/jats:sub>\n ) 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.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The finite-element model reproduced published uniaxial compression responses. BPNN achieved the best prediction of\n E<\/jats:italic>\n c<\/jats:sub>\n (R\n 2<\/jats:sub>\n = 0.9993 \u00b1 0.0003, NRMSE = 0.0256 \u00b1 0.0027, MAPE = 1.68 \u00b1 0.38%), whereas SVR performed best for\n \u03c3<\/jats:italic>\n c<\/jats:sub>\n (R\n 2<\/jats:sub>\n = 0.9987 \u00b1 0.0004, NRMSE = 0.0352 \u00b1 0.0030, MAPE = 2.23 \u00b1 0.45%). Response-surface analysis showed that\n E<\/jats:italic>\n t<\/jats:sub>\n and\n BV\/TV<\/jats:italic>\n primarily governed apparent stiffness, while failure stress was additionally sensitive to\n \u03b5<\/jats:italic>\n t<\/jats:sub>\n .\n <\/jats:p>\n <\/jats:sec>\n \n Discussion<\/jats:title>\n 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.<\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fbioe.2026.1870920","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T05:36:30Z","timestamp":1789450590000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Gyroid TPMS-based machine learning framework for rapid prediction of cancellous bone mechanical properties"],"prefix":"10.3389","volume":"14","author":[{"given":"Xinzhe","family":"Chen","sequence":"first","affiliation":[{"name":"South China University of Technology, School of Mechanical & Automotive Engineering","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiqing","family":"Chen","sequence":"additional","affiliation":[{"name":"South China University of Technology, School of Mechanical & Automotive Engineering","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengchong","family":"Lan","sequence":"additional","affiliation":[{"name":"South China University of Technology, School of Mechanical & Automotive Engineering","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"B1","volume-title":"In vivo","author":"Alberich Bayarri","year":"2010"},{"key":"B2","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/0021-9290(88)90167-4","article-title":"Elastic modulus of trabecular bone material","volume":"21","author":"Ashman","year":"1988","journal-title":"J. Biomechanics"},{"key":"B3","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/s0021-9290(03)00257-4","article-title":"Comparison of the elastic and yield properties of human femoral trabecular and cortical bone tissue","volume":"37","author":"Bayraktar","year":"2004","journal-title":"J. Biomechanics"},{"key":"B4","doi-asserted-by":"publisher","first-page":"105213","DOI":"10.1016\/j.ijmecsci.2019.105213","article-title":"Compression failure characterization of cancellous bone combining experimental testing, digital image correlation and finite element modeling","volume":"165","author":"Belda","year":"2020","journal-title":"Int. J. Mech. Sci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1218","DOI":"10.1016\/j.bone.2006.06.016","article-title":"Influence of bone volume fraction and architecture on computed large-deformation failure mechanisms in human trabecular bone","volume":"39","author":"Bevill","year":"2006","journal-title":"Bone"},{"key":"B6","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.jmbbm.2013.04.014","article-title":"Within subject heterogeneity in tissue-level post-yield mechanical and material properties in human trabecular bone","volume":"24","author":"Carretta","year":"2013","journal-title":"J. Mech. Behav. Biomed. Mater."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1174","DOI":"10.1126\/science.996549","article-title":"Bone compressive strength: the influence of density and strain rate","volume":"194","author":"Carter","year":"1976","journal-title":"Science"},{"key":"B8","doi-asserted-by":"publisher","first-page":"3333","DOI":"10.1016\/j.jbiomech.2007.05.004","article-title":"Validation of a voxel-based fe method for prediction of the uniaxial apparent modulus of human trabecular bone using macroscopic mechanical tests and nanoindentation","volume":"40","author":"Chevalier","year":"2007","journal-title":"J. Biomechanics"},{"key":"B9","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1359\/jbmr.2000.15.1.32","article-title":"Variations in three-dimensional cancellous bone architecture of the proximal femur in female hip fractures and in controls","volume":"15","author":"Ciarelli","year":"2009","journal-title":"J. Bone Mineral Res."},{"key":"B10","doi-asserted-by":"publisher","first-page":"101782","DOI":"10.1016\/j.beem.2023.101782","article-title":"Bone health and menopause: osteoporosis prevention and treatment","volume":"38","author":"De","year":"2024","journal-title":"Best Practice and research:Clinical Endocrinology and Metabolism"},{"key":"B11","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1016\/j.jmbbm.2016.08.026","article-title":"Subject-specific musculoskeletal loading of the tibia: computational load estimation","volume":"65","author":"Garijo","year":"2017","journal-title":"J. Mech. Behav. Biomed. Mater."},{"key":"B12","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.ijengsci.2014.10.007","article-title":"3d plastic collapse and brittle fracture surface models of trabecular bone from asymptotic homogenization method","volume":"87","author":"Goda","year":"2015","journal-title":"Int. J. Eng. Sci."},{"key":"B13","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.1016\/j.jbiomech.2011.05.034","article-title":"Age-related changes in human trabecular bone: relationship between microstructural stress and strain and damage morphology","volume":"44","author":"Green","year":"2011","journal-title":"J. Biomechanics"},{"key":"B14","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.bonr.2015.10.001","article-title":"The micro-architecture of human cancellous bone from fracture neck of femur patients in relation to the structural integrity and fracture toughness of the tissue","volume":"3","author":"Greenwood","year":"2015","journal-title":"Bone Rep."},{"key":"B15","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1016\/j.bone.2013.06.028","article-title":"Micro-ct finite element model and experimental validation of trabecular bone damage and fracture","volume":"56","author":"Hambli","year":"2013","journal-title":"Bone"},{"key":"B16","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1002\/jor.1100180315","article-title":"Age, gender, and bone lamellae elastic moduli","volume":"18","author":"Hoffler","year":"2000","journal-title":"J. Orthop. Res."},{"key":"B17","doi-asserted-by":"publisher","first-page":"245","DOI":"10.32604\/cmc.2020.06284","article-title":"Microstructural modeling and multiscale mechanical properties analysis of cancellous bone","volume":"62","author":"Huang","year":"2020","journal-title":"Comput. Mater. and Continua"},{"key":"B18","first-page":"668","article-title":"Nanoindentation of trabecular bone-comparison with uniaxial testing of single trabecula","volume":"105","author":"Jirou\u0161ek","year":"2011","journal-title":"J. Chem. Listy"},{"key":"B19","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1016\/j.jbiomech.2003.08.010","article-title":"Mechanical properties, density and quantitative ct scan data of trabecular bone with and without metastases","volume":"37","author":"Kaneko","year":"2004","journal-title":"J. Biomechanics"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1016\/0021-9290(94)90056-6","article-title":"Predicting the compressive mechanical behavior of bone","volume":"27","author":"Keller","year":"1994","journal-title":"J. Biomechanics"},{"key":"B21","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1359\/jbmr.1997.12.4.641","article-title":"Composition and mechanical properties of cancellous bone from the femoral head of patients with osteoporosis or osteoarthritis","volume":"12","author":"Li","year":"2010","journal-title":"J. Bone and Mineral Res."},{"key":"B22","doi-asserted-by":"publisher","first-page":"106764","DOI":"10.1016\/j.cmpb.2022.106764","article-title":"Numerical modeling of cancellous bone damage using an orthotropic failure criterion and tissue elastic properties as a function of the mineral content and microporosity","volume":"219","author":"Megias","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1016\/j.bone.2006.06.013","article-title":"The interaction of microstructure and volume fraction in predicting failure in cancellous bone","volume":"39","author":"Nazarian","year":"2006","journal-title":"Bone"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1861","DOI":"10.1016\/j.spinee.2020.06.013","article-title":"Distribution of young\u2019s modulus at various sampling points in a human lumbar spine vertebral body","volume":"20","author":"Ogurkowska","year":"2020","journal-title":"Spine J."},{"key":"B25","doi-asserted-by":"publisher","first-page":"111860","DOI":"10.1016\/j.jbiomech.2023.111860","article-title":"Predicting trabecular arrangement in the proximal femur: an artificial neural network approach for varied geometries and load cases","volume":"161","author":"Pais","year":"2023","journal-title":"J. Biomechanics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"113083","DOI":"10.1016\/j.eswa.2019.113083","article-title":"Real-time biomechanical modeling of the liver using machine learning models trained on finite element method simulations","volume":"143","author":"Pellicer-Valero","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"B27","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1016\/j.jbiomech.2007.08.003","article-title":"Dependence of mechanical compressive strength on local variations in microarchitecture in cancellous bone of proximal human femur","volume":"41","author":"Perilli","year":"2008","journal-title":"J. Biomechanics"},{"key":"B28","doi-asserted-by":"publisher","first-page":"102115","DOI":"10.1016\/j.mtcomm.2021.102115","article-title":"Modeling tensile strength and suture retention of polycaprolactone electrospun nanofibrous scaffolds by artificial neural networks","volume":"26","author":"Reddy","year":"2021","journal-title":"Mater. Today Commun."},{"key":"B29","doi-asserted-by":"publisher","first-page":"3144","DOI":"10.1016\/j.jbiomech.2010.07.038","article-title":"The role of mineral content in determining the micromechanical properties of discrete trabecular bone remodeling packets","volume":"43","author":"Smith","year":"2010","journal-title":"J. Biomechanics"},{"key":"B30","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1016\/s0021-9290(98)00177-8","article-title":"The elastic properties of trabecular and cortical bone tissues are similar: results from two microscopic measurement techniques","volume":"32","author":"Turner","year":"1999","journal-title":"J. Biomechanics"},{"key":"B31","doi-asserted-by":"publisher","first-page":"108120","DOI":"10.1016\/j.cmpb.2024.108120","article-title":"Estimation of the in-plane ultimate stress of lamellar tissue as a function of bone mineral density and osteocyte lacunae porosity","volume":"248","author":"Vercher-Mart\u00ednez","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1055\/s-0028-1144106","article-title":"Das gesetz der transformation der knochen","volume":"19","author":"Wolff","year":"1893","journal-title":"DMW - Dtsch. Med. Wochenschr."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.1016\/j.jbiomech.2011.01.018","article-title":"Damage accumulation in vertebral trabecular bone depends on loading mode and direction","volume":"44","author":"Wolfram","year":"2011","journal-title":"J. Biomechanics"},{"key":"B34","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.bone.2013.02.019","article-title":"In vivo microdamage is an indicator of susceptibility to initiation and propagation of microdamage in human femoral trabecular bone","volume":"55","author":"Wu","year":"2013","journal-title":"Bone"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.actbio.2018.08.001","article-title":"Young\u2019s modulus of trabecular bone at the tissue level: a review","volume":"78","author":"Wu","year":"2018","journal-title":"Acta Biomater."},{"key":"B36","doi-asserted-by":"publisher","first-page":"113657","DOI":"10.1016\/j.matdes.2025.113657","article-title":"Novel strut-based stochastic lattice biomimetically designed based on the structural and mechanical characteristics of cancellous bone","volume":"251","author":"Yamada","year":"2025","journal-title":"Mater. and Des."},{"key":"B37","doi-asserted-by":"publisher","first-page":"113277","DOI":"10.1016\/j.matdes.2024.113277","article-title":"From computed tomography to 3d printed heterogeneous scaffolds: a novel approach to simulating bone characteristics using octree adaptive subdivision","volume":"245","author":"Yau","year":"2024","journal-title":"Mater. and Des."},{"key":"B38","article-title":"Indirect determination of material model parameters for single trabecula based on nanoindentation and three-point bending test","volume":"194","author":"Zl\u00e1mal","year":"2012","journal-title":"Eng. Mech."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1016\/s0021-9290(99)00111-6","article-title":"Elastic modulus and hardness of cortical and trabecular bone lamellae measured by nanoindentation in the human femur","volume":"32","author":"Zysset","year":"1999","journal-title":"J. Biomechanics"}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1870920\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T05:36:31Z","timestamp":1789450591000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1870920\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"references-count":39,"alternative-id":["10.3389\/fbioe.2026.1870920"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2026.1870920","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]},"article-number":"1870920"}}