The new digital equipment to acquire medical images (thermographic cameras, ultrasound, digital mammograms, etc.) allow us to combine anatomical information from various sources to the specific characteristics of the patients. These data (images) must be processed to enhance and extract features. In this area, image processing and pattern recognition techniques are very important, both to automate certain procedures and to facilitate the interaction and combination of data.
The purpose of this research is to assist in medical imaging diagnosis by integrating the main steps of image processing methods of feature extraction and knowledge in order to interpret images, identification of tissues and anatomical and functional structures. In this sense, we seek to conduct research to assist in the early diagnosis of problems and breast diseases classification (benign / malignant). The project goes from the acquisition of the images and their organization in databases, through their analysis using numerical methods, to a last stage, where machine learning techniques should be used in order to be made an extraction of knowledge from the breast images.
Camera used in the project FLIR SC-620
Resolution 640 x 480: Pixel = 45 μm