Breast Cancer Detection Through Spectrogram Generation from GANs-Simulated Microwave Imaging Data

Breast cancer is a leading cause of death among women worldwide. Early detection systems can be crucial for improving survival rates. This paper presents a new approach to breast cancer detection using microwave imaging data from phantom scans of breast tissues. To enhance the robustness of the data, Generative Adversarial Networks (GANs) are used to simulate the microwave imaging dataset. The S<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">11</inf> and S<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">12</inf> parameters in this dataset are used to generate frequency spectrograms using Fourier analysis. These spectrograms are used as input to deep learning classification models used to classify the cancerous and non-cancerous data. This approach demonstrates promising accuracy and generalizability.