Computational intelligence based design of implant for varying bone conditions

Abstract

The objective is to make the strain deviation before and after implantation adjacent to the femoral implant as close as possible to zero. Genetic algorithm is applied for this optimization of strain deviation, measured in eight separate positions. The concept of composite desirability is introduced in such a way that if the microstrain deviation values for all eight cases are 0, then the composite desirability is 1. Artificial neural network (ANN) models are developed to capture the correlation of the microstrain in femur implants using the data generated through finite element simulation. Then, the ANN model is used as the surrogate model, which in combination with the desirability function serves as the objective function for optimization. The optimum achievable deviation was found to vary with the bone condition. The optimum implant geometry varied for different bone condition, and the findings act as guideline for designing patient-specific implant.

Design optimization of effective modulus through variation in pore geometries of Stainless Steel 316L

“…Hence, an artificial neural network (ANN) [22] metamodel, developed from the FEA simulation data, along with desirability function [23] is used as the objective function. Similar approaches using statistical and artificial intelligence methods are found in literature [24][25][26][27]. In present study stainless steel (316L) material is considered for the analysis.…”

Application of finite element analysis to tissue differentiation and bone remodelling approaches and their use in design optimization of orthopaedic implants: A review

“…GA was extensively used in the optimization of such problems with a large number of parameters, or a need for a detailed solution is sought after. 157,158 A study 159 on combined NN-desirability function-GA methodology was implemented to study shape optimization of a femoral implant by minimizing the strain deviation between the intact and implanted prosthesis. Very recently, a similar investigation 5 on the NN-GA technique was employed for the first time to assess the design optimization of implant macro-textures with the sole objective of maximizing the amount of bone growth over the implant surface.…”

Computational intelligence based design of biomaterials

“…Similar knowledge imprecise CI methods using ANFIS and whale optimization algorithm (Sai et al, 2020) were chosen for the optimization of polylactic acid implants by printing it through fusion deposition method. Chatterjee et al (2019) have used CI techniques (ANN/GA) to have the zero-strain difference adjacent to the femoral implant before and after implanting it. ANN meta-models generated through FEA simulation have been used as an objective function for the GA based optimization using the desirability functions of the ANN models.…”