Abstract
Early and accurate detection of breast cancer is a critical part of the strategy to reduce mortality associated with this prevalent disease. We propose to develop techniques based on applying the thermal impedance method and artificial intelligence to detect the origin of the heat source (abnormal cancer metabolism) and its size. The low sensitivity to tiny and deep tumours, usually found when analyzing surface temperatures using thermal imaging, is circumvented by utilizing the concept of thermal impedance and artificial intelligence techniques such as deep learning. The thermal model’s development and the database’s creation based on its solution are described. It also presents the choice of detectable parameters in the thermal image, deep learning libraries and network training using convolutional neural networks. Estimates of the location and size of tumours using thermographic images obtained from simulated thermal models of a breast based on a Cartesian geometry and a scanned geometric shape of an anatomical phantom model are also described.
