Genetic algorithms for estimating the biomechanical behavior of breast tissues

The accuracy of the patient-specific biomechanical models of the breast is a major concern for applications related with simulation, surgical guidance or cancer diagnosis. Being able to predict the localization of a lesion depends on the realism of the selected model. However, obtaining a realistic model of the breast tissues is not straightforward since the biomechanical parameters of the breast internal tissues vary significantly from one patient to another. This paper presents an iterative search algorithm which is able to obtain the parameters of a proposed biomechanical model. A methodology based on genetic algorithms was used in order to estimate the biomechanical model of the breast tissues. The similarity between the estimated model and the real model presents an overlap of about 94% and a maximum average distance below 1mm. This algorithm can be easily translated to real cases.