Hybrid Genetic Algorithm and Particle Swarm Optimization Based Microwave Tomography for Breast Cancer Detection

Abstract

A study on the development of a microwave tomography imaging algorithm for detecting the malignant tumor in the breast is presented. Tomography modality is based on the electromagnetic reflections generated by the dielectric contrast between breast tissue types at microwave frequencies. In the tomography method, finite difference time domain method (FDTD) has been used as a technique for calculating electromagnetic scattered fields. In this paper, we propose a novel hybrid optimization technique for solving the inverse scattering problem which uses the binary Genetic algorithm (BGA) and binary particle swarm optimization (BPSO). The convergence rate of this proposed algorithm is around 4 times better than the regular BGA. The proposed FDTD/hybrid BGA-BPSO method has the ability to reconstruct the heterogeneous and dispersive breast tissues to provide a quantitative image of permittivity and conductivity profile of the breast. The proposed technique is capable to detect the size, location and permittivity and conductivity of the tumor even though it is surrounded by benign and fibroglandular tissues.