Roger Resmini

Breast thermography from an image processing viewpoint: A survey

Abstract Breast cancer is the leading cause of death among women. This fact justifies researches to reach early diagnosis, improving patients’ life expectancy. Moreover, there are other pathologies, such as cysts and benign neoplasms that deserve investigation. In the last ten years, the infrared thermography has shown to be a promising technique to early diagnosis of breast pathologies. Works on this subject presented results that justify the thermography as a complementary exam to detect breast diseases. Several papers on the use of infrared imaging for breast screening can be found in the current medical literature. This survey explores and analyses these works in the light of their applications in computer vision. Consequently, the comments are organized according to the main steps of pattern recognition systems. These include: image acquisition protocols, exams storage, segmentation methods, feature extraction, classification or diagnostic and computer modelling. Main contributions of discussed papers are summarized in tables to provide a structured vision of the aspects involved in breast thermography.

Combining approaches for early diagnosis of breast diseases using thermal imaging

This paper presents a combination of efforts on the construction of a tool to help in the diagnosis by infrared breast images. It considers from the basic problem of image acquisition and storage in a database to the automatic extraction of the region of interest of each breast (left and right), the feature extraction, the decision and the limits of the diagnosis as well. The main objective of this study is the analysis of the viability of the use of the IR images for automatic detection of pathologies by texture symmetric analysis. Moreover numerical simulations and experimentations are developed in order to analyse the relation between the internal temperature of the breast and the temperature on the breast surface during the image acquisition.

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.