Atherosclerosis is one of the leading causes of mortality in the western world. Computed tomography angiography (CTA) is the conventional imaging method used for pre-surgery assessment of the blood flow within the carotid vessel. In this paper, we present a proof of concept of a novel, fast and operator independent protocol for the automatic detection (seeding) of the carotid arteries in CTA in the thorax and upper neck region. The dataset is composed of 14 patients' CTA images of the neck region. The performance of this method is compared with manual seeding by four trained operators. Inter-operator variation is also assessed based on the dataset. The minimum, average and maximum coefficient of variation among the operators was (0, 2, 5 %), respectively. The performance of our method is comparable with the state of the art alternative, presenting a detection rate of 75 and 71 % for the lowest and uppermost image levels, respectively. The mean processing time is 167 s per patient versus 386 s for manual seeding. There are no significant differences between the manual and automatic seed positions in the volumes (p = 0.29). A fast, operator independent protocol was developed for the automatic detection of carotid arteries in CTA. The results are encouraging and provide the basis for the creation of automatic detection and analysis tools for carotid arteries.
Keywords: Atherosclerosis; Automatic image analysis; Carotid angiography; Machine vision.