Beyin Bilgisayarlı Tomografi Görüntülerinde Yapay Zeka Tabanlı Beyin Damar Hastalıkları Tespiti

Abstract

Cerebrovascular disease (CVD) causes paralysis and even mortality in humans due to blockage or bleeding of brain vessels. The early diagnosis of the CVD type by the specialist can avoid these casualties with a correct course of treatment. However, it is not always possible to recruit enough specialists in hospitals or emergency services. Therefore, in this study, an artificial intelligence (AI)-based clinical decision support system for CVD detection from brain computed tomography (CT) images is proposed to improve the diagnostic results and relieve the burden of specialists. The deep learning model, a subset of AI, was implemented through a two-step process in which CVD is first detected and then classified as ischemic or hemorrhagic. Moreover, the developed system is integrated into our custom-designed desktop application that offers a user-friendly interface for CVD diagnosis. Experimental results prove that our system has great potential to improve early diagnosis and treatment for specialists, which contributes to the recovery rate of patients.