Computer Aided Detection of Pulmonary Embolism in Computed Tomography Angiography Images

Abstract

Pulmonary Embolism (PE), one of the circulatory system problems, is the clinical result at the end of that the lung artery or one or a few branches of them are bunged up by clot of blood. Besides it is a hard disease to diagnose, early diagnosis and treatment of it can save lives. In this study, a new CAD system is proposed for detection of PE in CTA images. Firstly, lung was segmented and Mediastinum Region (MR) was determined. Secondly, lung vessel segmentation was carried out. Lastly, PEs were detected according to region, intensity, and the size of PEs in lung vessel tree. Data set belongs to 15 patients were examined. 210 PEs were determined by the radiologists manually. 181 of them were detected as PE by our CAD system. According to the proposed method, 86.2% of sensitivity with 13.1 false positive per data sets (FP/ds) is obtained.