Genetic Algorithms and Vascular Graft Optimization

Abstract

The optimization of graft and anastomotic configurations with regard to blood dynamics is the major target of this study. Adeveloped multi-objective genetic algorithm is considered in order to reach optimal graft geometries for idealized arterial bypasssystems of fully occluded host arteries. An artificial neural network simulating hemodynamic specific conditions is introduced inorder to reduce the genetic algorithm computational time. Input data values are constrained within pre-defined boundaries for graftgeometric parameters and the correspondent target values are solutions for blood velocity and shear stress functions calculated with afinite element simulator. Optimal solutions are within a family of design points reached at the end of the optimization process.