A Feasibility Study of 2-D Microwave Thorax Imaging Based on the Supervised Descent Method

In this paper, the application of supervised descent method (SDM) for 2-D microwave thorax imaging is studied. The forward modeling problem solved by finite element-boundary integral (FE-BI) method. According to prior information human thorax, a 3-ellipse training set generated offline. Then, average direction between an initial background model and models calculated. Finally, reconstruction testing achieved based on directions online. feasibility using One-Step SDM Numerical results indicate that structural can be reconstructed. It has potential real-time in future clinical diagnosis.