Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Sep 13, 2025

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects
08:39

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

176

Multi-Objective Machine Learning Optimization of Cylindrical TPMS Lattices for Bone Implants.

Mansoureh Rezapourian1, Ali Cheloee Darabi2, Mohammadreza Khoshbin3

  • 1Department of Mechanical and Industrial Engineering, Tallinn University of Technology, 19086 Tallinn, Estonia.

Biomimetics (Basel, Switzerland)
|July 25, 2025
PubMed
Summary

Related Concept Videos

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

101
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
101

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Self-Propagating High-Temperature Synthesis as an Enabling Route for High-Entropy MAX Phases.

Materials (Basel, Switzerland)·2026
Same author

Patient-Specific Lattice Implants for Segmental Femoral and Tibial Reconstruction (Part 1): Defect Patterns, Fixation Strategies and Reconstruction Options-A Review.

Biomimetics (Basel, Switzerland)·2026
Same author

Patient-Specific Lattice Implants for Segmental Femoral and Tibial Reconstruction (Part 2): CT-Based Personalization, Design Workflows and Validation-A Review.

Biomimetics (Basel, Switzerland)·2026
Same author

Wear Performance of a Physical Vapour Deposition-Coated, Spark Plasma Sintered TiB<sub>2</sub>/Ti Composite Lubricated with Externally Introduced hBN at Temperatures up to 900 °C.

Materials (Basel, Switzerland)·2025
Same author

Effect of Laser Surface Texturing and Fabrication Methods on Tribological Properties of Ti6Al4V/HAp Biocomposites.

Materials (Basel, Switzerland)·2025
Same author

Bioinspired and Multifunctional Tribological Materials for Sliding, Erosive, Machining, and Energy-Absorbing Conditions: A Review.

Biomimetics (Basel, Switzerland)·2024
This summary is machine-generated.

This study optimizes triply periodic minimal surface (TPMS) lattices for bone implants using artificial neural networks and multi-objective optimization. Size-specific designs were developed, balancing mechanical performance and surface efficiency for personalized medicine applications.

Area of Science:

  • Biomaterials Engineering
  • Computational Biology
  • Mechanical Engineering

Background:

  • Triply Periodic Minimal Surface (TPMS) lattices offer promising mechanical properties for bone implants.
  • Optimizing TPMS lattice designs requires balancing multiple performance objectives and accounting for anatomical variations.
  • Existing design frameworks often lack specificity for different implant sizes.

Purpose of the Study:

  • To develop a multi-objective optimization framework for designing size-specific TPMS lattices for bone implants.
  • To predict key mechanical and surface properties using an artificial neural network (ANN) surrogate model.
  • To tailor lattice designs for small, medium, and large anatomical variations.

Main Methods:

  • A multi-objective optimization framework utilizing the NSGA-II algorithm was employed.
Keywords:
Johnson–Cook failure modelPareto front analysisartificial neural network (ANN)bone implantsfinite element analysis (FEA)machine learningmechanical property predictionmulti-objective optimizationsize-specific implant designtriply periodic minimal surfaces (TPMS)

More Related Videos

Precision Measurements and Parametric Models of Vertebral Endplates
10:35

Precision Measurements and Parametric Models of Vertebral Endplates

Published on: September 17, 2019

6.6K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K

Related Experiment Videos

Last Updated: Sep 13, 2025

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects
08:39

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

176
Precision Measurements and Parametric Models of Vertebral Endplates
10:35

Precision Measurements and Parametric Models of Vertebral Endplates

Published on: September 17, 2019

6.6K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
  • An artificial neural network (ANN) was trained to predict ultimate stress, energy absorption, surface area-to-volume ratio, and relative density.
  • Designs were categorized and optimized for small, medium, and large implant sizes, with relative density filtered between 20-40%.

    • Main Results:

    • 105 Pareto-optimal designs were identified, with 75 retained after filtering for biologically relevant relative density.
    • SHapley Additive exPlanations (SHAP) analysis indicated lattice thickness and unit cell size as dominant design parameters.
    • Distinct performance trends were observed across different implant size groups.

    Conclusions:

    • The developed framework effectively balances competing design objectives for TPMS lattices.
    • Size-specific optimization enables the selection of tailored lattices for bone implant applications.
    • This approach offers a reproducible pathway for optimizing bioarchitectures, advancing personalized medicine in implant development.