Volumetric examinations of the aorta are nowadays of crucial importance for the management of critical pathologiessuch as aortic dissection, aortic aneurism, and other pathologies, which affect the morphology of the artery. Theseexaminations usually begin with the acquisition of a Computed Tomography Angiography (CTA) scan from thepatient, which is later on postprocessed to reconstruct the 3D geometry of the aorta. The first postprocessing step isreferred to as segmentation. Different algorithms have been suggested for the segmentation of the aorta; includinginteractive methods, as well as fully automatic methods. Interactive methods need to be fine-tuned on each singleCTA scan and result in longer duration of the process, whereas fully automatic methods require the possession of alarge amount of labeled training data. In this work, we introduce a hybrid approach by combining a deep learningmethod with a consolidated interaction technique. In particular, we trained a 2D and a 3D U-Net on a limited numberof patches extracted from 25 labeled CTA scans. Afterwards, we use an interactive approach, which consists indefining a region of interest (ROI) by just placing a seed point. This seed point is later used as the center of a 2D or3D patch to be fed to the 2D or 3D U-Net, respectively. Due to the low content variation of these patches, this methodallows to correctly segment the ROIs without the need for parameter tuning for each dataset and with a smallertraining dataset, requiring the same minimal interaction as state-of-the-art interactive methods. Later on, the newsegmented CTA scans can be further used to train a convolutional network for a fully automatic approach.
展开▼
