Regresar

Automatic segmentation of the thoracic aorta in cardiac computed tomography images

Abstract:

The article proposes a technique for automatic segmentation of the thoracic aorta (TAA), also called the descending external aorta, in 10 three-dimensional (3-D) cardiac images of multi-cut computed tomography, belonging to the same subject. The mentioned technique consists of the stages of filtering and segmentation. The filtering step, called global similarity enhancement, is used to minimize both Poisson noise and the impact of the ladder artifact on image quality. This type of enhancement consists in the application of a bank of filters, softeners and a border detector, whose purpose is to generate an image in which the information of the anatomical structures that make up the original images are grouped together. On the other hand, to generate the 3-D morphology of the TAA, a segmentation stage is applied which considers the filtered images and a clustering algorithm based on regions growth. The proposed strategy generates the 3-D segmentations of TAA in all the images that make up the complete cardiac cycle of the subject considered. In order to quantify the performance of the referred technique, the Dice coefficient was considered, obtaining a good correlation between the automatic segmentations and the manual ones generated by a cardiologist. Automatically generated segmentations may be helpful in detecting certain pathologies that affect both the aorta and anatomical structures associated with it, such as the aorta and left ventricle.