Revolutionizing Breast Cancer Detection Using Thermal Imaging with Deep Learning Analysis

Breast cancer is one of the vulnerable diseases in women. Early diagnosis of breast cancer improves treatment outcomes and survival rates. This work delves into an approach by leveraging the joint capabilities of VGG-16 and Dilated Convolutions (DC) in Infrared Mammary Analysis (IRMA) to enhance the detection of breast cancer. The collaboration with VGG-16 brings an added layer of precision to the analysis of thermal images, contributing to an integrated methodology that demonstrates notable accuracy. This method not only reshapes the landscape of breast cancer diagnostics but also highlights the potential of Dilated Convolutions in overcoming spatial limitations inherent in thermal imaging. In this proposed approach, the combined VGG-16 and DC method gives better response compared with similar algorithms. Based on the various parameter metrics this approach gives considerable results for the chosen dataset.