Medical Imaging has been widely used for the diagnosis and detection of several illnesses for decades, as it can capture potentially important characteristics of the body in a non-invasive manner. The advent of Digital Image Processing techniques and afterwards of Machine Learning methods in the area was another important milestone for the analysis of medical images, as many parts of the physician’s procedure for detection of abnormalities could be aided or improved by computers, strengthening the reliability of such processes. The PATREO research group works on the whole pipeline of detection and classification of mammograms, including several aspects of pre and postprocessing of these exams. Our main research area in Medical Images is focused on the automatic detection of abnormalities on mammographic images using Deep Learning, providing physicians with an automated second opinion.
