Temperature changes in the body have been recognized as an indicator of illness for centuries, also localized temperature variations due to inflammatory or ischemic events are common in a great variety of diseases, these changes are due to changes in blood perfusion which are partly responsible, along with the metabolic heat generation of tissue, for the local temperature of tissue and organs. In the case of cancerous breast tumors there is an increase in vascularity due to angiogenesis and a higher metabolic rate compared to healthy tissue, which induces an increase in the local temperature of the tumor, this increase in temperature generates a small increase in skin temperature that can be detected with modern infrared imaging equipment. In this work the thermal characteristics, delta-T, vascularity and average temperature of the breast, of patients with cancerous and benign tumors were measured in order to determine differences in thermal signatures, which might help increase the usefulness of thermography as an adjunct tool in breast cancer screening. This thermal parameters were then correlated to the BIRADS and with histopathological findings. Results show some correlation between the thermal parameters and with malignancy of the tumors.
Temperature patterns of the breast measured using infrared thermography have been used to detect changes in blood perfusion that can occur due to inflammation, angiogenesis, or other pathological causes. In this work, 94 thermograms of patients with suspected breast cancer were analyzed using an automatic classification method, based on a convolutional neural network. In particular, our approach uses a deep convolutional neural network (CNN) with transfer learning to automatically classify thermograms into two different tasks: normal and abnormal thermograms, and malign and benign lesions. Class Activation Mapping is used to show how the network can focus on the affected areas without having received this information. Several measurements were carried out to validate the performance of the network in each task and these results suggest that deep convolutional neural networks with transfer learning are able to detect thermal anomalies in thermograms with sensitivity similar to that of a human expert, even in cohorts with a low prevalence of breast cancer.