Automatic segmentation of the abdominal Aorta from CT images
Automatic segmentation of the abdominal Aorta from CT images: an initial approach towards the aortic Aneurysm detection
Versandkostenfrei!
Versandfertig in 6-10 Tagen
32,99 €
inkl. MwSt.
PAYBACK Punkte
16 °P sammeln!
We present a new method for the segmentation and the detection of human Abdominal Aorta in CT images. Our method is divided into two parts. In the first part we estimate the position and the dimension of the aortic lumen using state-of-the-art object tracking techniques. The second part employs curve fitting methods in order to detect the boundaries of the aortic lumen with accuracy, based on the estimation of the first part. In particular, the proposed method uses the Kalman Filter to track the aortic cross-section in consecutive CT images. The observations needed by the Kalman procedure are ...
We present a new method for the segmentation and the detection of human Abdominal Aorta in CT images. Our method is divided into two parts. In the first part we estimate the position and the dimension of the aortic lumen using state-of-the-art object tracking techniques. The second part employs curve fitting methods in order to detect the boundaries of the aortic lumen with accuracy, based on the estimation of the first part. In particular, the proposed method uses the Kalman Filter to track the aortic cross-section in consecutive CT images. The observations needed by the Kalman procedure are extracted with the Circle Hough Transformation, based on the assumption that the morphological structure of the aortic cross-section is approximately a circle. A robust Level Set method is then applied to compensate the approximation error and efficiently estimate the cross-section. The algorithms and the mathematical tools developed during the project prove feasibility for an accurate and reliable method for the segmentation of the abdominal aorta from CT data, that in the future could be used to benefit patients with aortic aneurysms.
Andere Kunden interessierten sich für
