Application Of Infrared Images To Diagnosis And Modeling Of Breast

This chapter presents some developments and researches on using breast infrared images in Brazil (Visual Lab group of the Federal Fluminense University). These researches focus on comparing protocols for data acquisition using a FLIR SC 620 infrared (IR) camera; preprocessing the acquired data (using operations such as region of interest or ROI extraction, image registration and some other operations to prepare the images or thermal matrices to be used in computations); 3D reconstruction and, diagnostic recommendations from the IR data. These are steps for development of computer tools for screening breast diseases, mainly, to be used on public health system (named in Brazil: "Sistema Unico de Saude"-SUS). After experimentations and comparisons among the diversity of recommendations and ways of data acquisition reported in the literature, we propose a new protocol to IR data capture and storage. With these, we developed a web site that can be used by all researchers interested in development of works in such subject. The site has public access and presents several ground truths of intermediated developments of the research as segmentation of the ROI, sets of features to be used for comparing artificial intelligence methods for decision making, and some techniques for ROI registration. Our intension is to provide materials to those interested in infrared researches for breast disease. For the development of IR applications are very important compare outcomes in disease detection (and diagnosis) and to use different strategies for features extraction, decision-making, and dimensionality reduction. However, in order to promote fair conditions for comparisons, we have to begin in a more standardized way to go further and for this we invite all interest in the same theme to use a unified procedure for data acquisition.