Application Research Of Microwave Imaging For Breast Cancer Based On Improved Quantum Genetic Algorithm

Microwave near-field imaging of breast cancer, which is using high-frequency microwave radiation signal to detect human breast, and collecting scattered data to reconstruct the distribution of the dielectric constants of breast issue. Strong nonlinear and complex characteristics must be concerned in the reaction. Applications of electromagnetic imaging much depend upon the reconstruction algorithms developments. Unfortunately, there are many problems need to be handled, such as: low efficiency, uncomfortable precision, hard to use known information, ill-posed, inverse-problem, etc.Aiming at difficulty in solving inverse scatter problem and outstanding global optimization capability of quantum genetic algorithm, we present the application of quantum genetic algorithm (QGA) to reconstruct the images of dielectric constant distribution of breast tissue. By defining an objective function, reconstruction is converted to be an optimization process of searching an optimum parameter configuration. Meanwhile, due to the large complexity of case data,we apply an adaptive adjustment strategy and Niche technology to make improvements in the selection of quantum rotation gate, which can speed up the update rate of population so as to convergence faster.This is a new idea in the study, which is applying improved Quantum Genetic Algorithm (IGQA) to solve microwave based breast inverse imaging system. Furthermore, we design a simulation to verify its practicability. Obviously, it’s an ideal method to solve noninvasive problem in biomedical engineering.Finally, with the combination of MATLAB and Visual Studio C++, we apply imaging module based on quantum genetic algorithm to near-field microwave breast cancer imaging terminal. To clearly show the distribution of dielectric constant, we use different color look up table corresponding to different dielectric value. The tomographic images indicate that using IGQA to inverse image can clearly show the permittivity distribution of breast inner space. Moreover, we can effectively identify the distribution of suspicious tumor.