Automatic detection of anatomical landmarks of the aorta in CTA images.

Computed tomography angiography (CTA) is one of the most common vascular imaging modalities. However, for clinical use, it still requires laborious manual analysis. This study demonstrates the feasibility of a fully automated technology for the accurate detection and identification of several anatomical reference points (landmarks), commonly used in intravascular imaging. This technology uses two different approaches, specially designed for the detection of aortic root and supra-aortic and visceral branches. In order to adjust the parameters of the developed algorithms, a total of 33 computed tomography scans with different types of pathologies were selected. Furthermore, a total of 30 independently selected computed tomography scans were used to assess their performance. Accuracy was evaluated by comparing the locations of reference points manually marked by human experts with those that were automatically detected. For supra-aortic and visceral branches detection, average values of 91.8 % for recall and 98.8 % for precision were obtained. For aortic root detection, the average difference between the positions marked by the experts and those detected by the computer was 5.7 ± 7.3 mm. Finally, diameters and lengths of the aorta were measured at different locations related to the extracted landmarks. Those measurements agreed with the values reported by the literature. Graphical abstract Schematic description of the proposed algorithm. The input includes an already segmented aorta (left), there are two main sub-processes related to the detection of branches and roots (center), and the output includes the segmented original aorta with the branches and the detected landmarks superimposed (right).

Automatic estimation of the aortic lumen geometry by ellipse tracking.

PURPOSE: The shape and size of the aortic lumen can be associated with several aortic diseases. Automated computer segmentation can provide a mechanism for extracting the main features of the aorta that may be used as a diagnostic aid for physicians. This article presents a new fully automated algorithm to extract the aorta geometry for either normal (with and without contrast) or abnormal computed tomography (CT) cases. METHODS: The algorithm we propose is a fast incremental technique that computes the 3D geometry of the aortic lumen from an initial contour located inside it. Our approach is based on the optimization of the 3D orientation of the cross sections of the aorta. The method uses a robust ellipse estimation algorithm and an energy-based optimization technique to automatically track the centerline and the cross sections. The optimization involves the size and eccentricity of the ellipse which best fits the aorta contour on each cross-sectional plane. The method works directly on the original CT and does not require a prior segmentation of the aortic lumen. We present experimental results to show the accuracy of the method and its ability to cope with challenging CT cases where the aortic lumen may have low contrast, different kinds of pathologies, artifacts, and even significant angulations due to severe elongations. RESULTS: The algorithm correctly tracked the aorta geometry in 380 of 385 CT cases. The mean of the dice similarity coefficient was 0.951 for aorta cross sections that were randomly selected from the whole database. The mean distance to a manually delineated segmentation of the aortic lumen was 0.9 mm for sixteen selected cases. CONCLUSIONS: The results achieved after the evaluation demonstrate that the proposed algorithm is robust and accurate for the automatic extraction of the aorta geometry for both normal (with and without contrast) and abnormal CT volumes.