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
  • [11] Porosity of 3D biomaterial scaffolds and osteogenesis
    Karageorgiou, V
    Kaplan, D
    [J]. BIOMATERIALS, 2005, 26 (27) : 5474 - 5491
  • [12] Tissue engineering: The challenges ahead
    Langer, RS
    Vacanti, JP
    [J]. SCIENTIFIC AMERICAN, 1999, 280 (04) : 86 - 89
  • [13] Developing porosity of poly(propylene glycol-co-fumaric acid) bone graft substitutes and the effect on osteointegration: A preliminary histology study in rats
    Lewandrowski, KU
    Gresser, JD
    Bondre, SP
    Silva, AE
    Wise, DL
    Trantolo, DJ
    [J]. JOURNAL OF BIOMATERIALS SCIENCE-POLYMER EDITION, 2000, 11 (08) : 879 - 889
  • [14] Bone defect animal models for testing efficacy of bone substitute biomaterials
    Li, Ye
    Chen, Shu-Kui
    Li, Long
    Qin, Ling
    Wang, Xin-Luan
    Lai, Yu-Xiao
    [J]. JOURNAL OF ORTHOPAEDIC TRANSLATION, 2015, 3 (03) : 95 - 104
  • [15] The Bone Extracellular Matrix in Bone Formation and Regeneration
    Lin, Xiao
    Patil, Suryaji
    Gao, Yong-Guang
    Qian, Airong
    [J]. FRONTIERS IN PHARMACOLOGY, 2020, 11
  • [16] A data-driven computational homogenization method based on neural networks for the nonlinear anisotropic electrical response of graphene/polymer nanocomposites
    Lu, Xiaoxin
    Giovanis, Dimitris G.
    Yvonnet, Julien
    Papadopoulos, Vissarion
    Detrez, Fabrice
    Bai, Jinbo
    [J]. COMPUTATIONAL MECHANICS, 2019, 64 (02) : 307 - 321
  • [17] Comparison of the design maps of TPMS based bone scaffolds using a computational modeling framework simultaneously considering various conditions
    Lu, Yongtao
    Huo, Yi
    Zou, Jia'ao
    Li, Yanchen
    Yang, Zhuoyue
    Zhu, Hanxing
    Wu, Chengwei
    [J]. PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART H-JOURNAL OF ENGINEERING IN MEDICINE, 2022, 236 (08) : 1157 - 1168
  • [18] Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials
    Ma, Wei
    Cheng, Feng
    Liu, Yongmin
    [J]. ACS NANO, 2018, 12 (06) : 6326 - 6334
  • [19] Selective Laser Melting: A Unit Cell Approach for the Manufacture of Porous, Titanium, Bone In-Growth Constructs, Suitable for Orthopedic Applications. II. Randomized Structures
    Mullen, Lewis
    Stamp, Robin C.
    Fox, Peter
    Jones, Eric
    Ngo, Chau
    Sutcliffe, Christopher J.
    [J]. JOURNAL OF BIOMEDICAL MATERIALS RESEARCH PART B-APPLIED BIOMATERIALS, 2010, 92B (01) : 178 - 188
  • [20] Compensating the anisotropic mechanical properties of electron beam melting-based Gyroid scaffolds using structural design
    Peng, Xing
    Huang, Qiyuan
    Zhang, Guoxian
    Li, Junyan
    Zhang, Xiaogang
    Lu, Yongtao
    Jin, Zhongmin
    [J]. INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES, 2022, 226