A Microwave-Thermography Hybrid Technique for Breast Cancer Detection

Abstract

This paper proposes a hybrid breast cancer detection modality consisting of microwaves as a radiation source and an infrared thermography method as a heat-imaging recorder, supported by a Convolution Neural Network (CNN). This hybrid method is based on the difference in the transmitted electromagnetic power between healthy and tumorous breasts. This variation in transmitted power results from the electrical property variance between healthy and cancerous tissues. Under microwave radiation, the power of the transmitted waves leads to a heat distribution pattern on a sensitive screen placed under the breast. This work utilizes the change in the heat pattern to indicate the presence of abnormality inside the breast. Involving a CNN elevates the proposed technique’s detection capability and extracts quantitative data that characterize the tumor’s location and size. The proposed modality shows a capability to detect and determine the size and location of an artificial tumor with a 5 mm radius and a 2:1 permittivity contrast with normal tissue.