The Barrett's Esophagus is usually hard to detect at the early stages of the esophageal lesion, being not correctly observed in the cancerous tissue evaluation so often. The development of automatic evaluation systems of such illness may be very useful, thus assisting the experts in the neoplastic region detection. With the strong growth of the machine learning techniques aiming to improve the medical diagnosis efficiency, the use of such techniques characterize a strong scenario to be explored for the early diagnosis of Barrett's esophagus. Notice this disease is responsible for the growth of esophageal adenocarcinoma worldwide, which can explained by some risk factors, such as obesity, smoking and late medical diagnosis. Given that a number of works have used artificial intelligence tools to assist the automatic medical diagnosis, this project proposes the development of new computer vision- and machine learning-driven techniques to assist the automatic diagnosis of the Barrett's esophagus.
News published in Agência FAPESP Newsletter about the scholarship: