Breast cancer classification on thermograms using deep CNN and transformers
Ella Mahoro, Moulay A. Akhloufi
Abstract
Breast thermography is a screening approach for breast cancer detection by measuring the breast skin temperature. Breast cancer is the most common cancer among women and can affect either women or men. Its early diagnosis and treatment reduce deaths and increase survival chances. The use of deep learning algorithms and techniques has made it easier to detect breast cancer in its early stages, but some challenges remain. In this work, we propose a breast cancer detection system. In the first step, TransUNet, a vision-based Transformer, is used to segment the breast region and separate it from the rest of the body. In the second step, four different models such as EfficientNet-B7, ResNet-50, VGG-16 and DenseNet-201 are used to classify the dataset into three types: healthy, sick, and unknown. The best accuracy achieved is 97.26%, sensitivity of 97.26% and specificity of each class healthy, sick, unknown is 100%, 96.94% and 99.72% respectively with the ResNet-50 model.