Inverse design of anisotropic bone scaffold based on machine learning and regenerative genetic algorithm

被引:11
作者
Liu, Wenhang [1 ]
Zhang, Youwei [1 ]
Lyu, Yongtao [1 ,2 ]
Bosiakov, Sergei [3 ]
Liu, Yadong [4 ]
机构
[1] Dalian Univ Technol, Dept Engn Mech, Dalian, Peoples R China
[2] Dalian Univ Technol, DUT BSU joint Inst, Dalian, Peoples R China
[3] Belarusian State Univ, Fac Mech & Math, Minsk, BELARUS
[4] Dalian Univ Technol, Dalian Municipal Cent Hosp Affiliated, Dept Orthoped, Dalian, Peoples R China
来源
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY | 2023年 / 11卷
基金
中国国家自然科学基金;
关键词
machine learning; genetic algorithm; triply periodic minimal surfaces; inverse design; arrangement anisotropy; IMPLANTS; TITANIUM; POROSITY;
D O I
10.3389/fbioe.2023.1241151
中图分类号
Q81 [生物工程学(生物技术)]; Q93 [微生物学];
学科分类号
071005 ; 0836 ; 090102 ; 100705 ;
摘要
Introduction: Triply periodic minimal surface (TPMS) is widely used in the design of bone scaffolds due to its structural advantages. However, the current approach to designing bone scaffolds using TPMS structures is limited to a forward process from microstructure to mechanical properties. Developing an inverse bone scaffold design method based on the mechanical properties of bone structures is crucial.Methods: Using the machine learning and genetic algorithm, a new inverse design model was proposed in this research. The anisotropy of bone was matched by changing the number of cells in different directions. The finite element (FE) method was used to calculate the TPMS configuration and generate a back propagation neural network (BPNN) data set. Neural networks were used to establish the relationship between microstructural parameters and the elastic matrix of bone. This relationship was then used with regenerative genetic algorithm (RGA) in inverse design.Results: The accuracy of the BPNN-RGA model was confirmed by comparing the elasticity matrix of the inverse-designed structure with that of the actual bone. The results indicated that the average error was below 3.00% for three mechanical performance parameters as design targets, and approximately 5.00% for six design targets.Discussion: The present study demonstrated the potential of combining machine learning with traditional optimization method to inversely design anisotropic TPMS bone scaffolds with target mechanical properties. The BPNN-RGA model achieves higher design efficiency, compared to traditional optimization methods. The entire design process is easily controlled.
引用
收藏
页数:12
相关论文
共 35 条
  • [1] Additively manufactured metallic porous biomaterials based on minimal surfaces: A unique combination of topological, mechanical, and mass transport properties
    Bobbert, F. S. L.
    Lietaert, K.
    Eftekhari, A. A.
    Pouran, B.
    Ahmadi, S. M.
    Weinans, H.
    Zadpoor, A. A.
    [J]. ACTA BIOMATERIALIA, 2017, 53 : 572 - 584
  • [2] Application of deep learning neural network to identify collision load conditions based on permanent plastic deformation of shell structures
    Chen, Guorong
    Li, Tiange
    Chen, Qijun
    Ren, Shaofei
    Wang, Chao
    Li, Shaofan
    [J]. COMPUTATIONAL MECHANICS, 2019, 64 (02) : 435 - 449
  • [3] Scaffold Fabrication Technologies and Structure/Function Properties in Bone Tissue Engineering
    Collins, Maurice N.
    Ren, Guang
    Young, Kieran
    Pina, S.
    Reis, Rui L.
    Oliveira, J. Miguel
    [J]. ADVANCED FUNCTIONAL MATERIALS, 2021, 31 (21)
  • [4] Isotropic porous structure design methods based on triply periodic minimal surfaces
    Feng, Jiawei
    Liu, Bo
    Lin, Zhiwei
    Fu, Jianzhong
    [J]. MATERIALS & DESIGN, 2021, 210
  • [5] Demineralized bone matrix in bone repair: History and use
    Gruskin, Elliott
    Doll, Bruce A.
    Futrell, F. William
    Schmitz, John P.
    Hollinger, Jeffrey O.
    [J]. ADVANCED DRUG DELIVERY REVIEWS, 2012, 64 (12) : 1063 - 1077
  • [6] Design of maximum permeability material structures
    Guest, James K.
    Prevost, Jean H.
    [J]. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2007, 196 (4-6) : 1006 - 1017
  • [7] Use of Carbon-Fiber-Reinforced Composite Implants in Orthopedic Surgery
    Hak, David J.
    Mauffrey, Cyril
    Seligson, David
    Lindeque, Bennie
    [J]. ORTHOPEDICS, 2014, 37 (12) : 825 - 830
  • [8] Bone Regeneration Based on Tissue Engineering Conceptions - A 21st Century Perspective
    Henkel, Jan
    Woodruff, Maria A.
    Epari, Devakara R.
    Steck, Roland
    Glatt, Vaida
    Dickinson, Ian C.
    Choong, Peter F. M.
    Schuetz, Michael A.
    Hutmacher, Dietmar W.
    [J]. BONE RESEARCH, 2013, 1 : 216 - 248
  • [9] Scaffold Design and Manufacturing: From Concept to Clinic
    Hollister, Scott J.
    [J]. ADVANCED MATERIALS, 2009, 21 (32-33) : 3330 - 3342
  • [10] Mechanical properties of glenoid cancellous bone
    Kalouche, Ibrahim
    Crepin, Jerome
    Abdelmoumen, Samir
    Mitton, David
    Guillot, Genevieve
    Gagey, Olivier
    [J]. CLINICAL BIOMECHANICS, 2010, 25 (04) : 292 - 298