Aplicação de técnicas de reconhecimento de padrões em imagens de termografia para auxílio no diagnóstico de câncer de mama

Abstract

Breast cancer is the type of cancer that most affects women worldwide. New means of screening methods to detect the desease in early stages are fundamental for more efficient treatments and better recovery rates. Currently, mamography is the standart exam for breast cancer detection, a painfull and invasive exam witch exposes the pacient to ionizing radiation. Thermographic images are an alternative for detection of anomalies in the body behavior, that only needs a special camera. Although identifying such anomalies is subjective even for trained professionals, the work here presented has an accuracy of 86% with a sensibility of 100% for 67 pacient images.