Paper
16 April 2012 Computer-assisted diagnostic tool to quantify the pulmonary veins in sickle cell associated pulmonary hypertension
Guido H. Jajamovich, Vivek Pamulapati, Shoaib Alam, Alem Mehari, Gregory J. Kato, Bradford J. Wood, Marius George Linguraru
Author Affiliations +
Abstract
Pulmonary hypertension is a common cause of death among patients with sickle cell disease. This study investigates the use of pulmonary vein analysis to assist the diagnosis of pulmonary hypertension non-invasively with CT-Angiography images. The characterization of the pulmonary veins from CT presents two main challenges. Firstly, the number of pulmonary veins is unknown a priori and secondly, the contrast material is degraded when reaching the pulmonary veins, making the edges of these vessels to appear faint. Each image is first denoised and a fast marching approach is used to segment the left atrium and pulmonary veins. Afterward, a geodesic active contour is employed to isolate the left atrium. A thinning technique is then used to extract the skeleton of the atrium and the veins. The locations of the pulmonary veins ostia are determined by the intersection of the skeleton and the contour of the atrium. The diameters of the pulmonary veins are measured in each vein at fixed distances from the corresponding ostium, and for each distance, the sum of the diameters of all the veins is computed. These indicators are shown to be significantly larger in sickle-cell patients with pulmonary hypertension as compared to controls (p-values < 0.01).
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Guido H. Jajamovich, Vivek Pamulapati, Shoaib Alam, Alem Mehari, Gregory J. Kato, Bradford J. Wood, and Marius George Linguraru "Computer-assisted diagnostic tool to quantify the pulmonary veins in sickle cell associated pulmonary hypertension", Proc. SPIE 8317, Medical Imaging 2012: Biomedical Applications in Molecular, Structural, and Functional Imaging, 83171J (16 April 2012); https://doi.org/10.1117/12.910966
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Veins

Photovoltaics

Control systems

Heart

Pulmonary hypertension

Image segmentation

Single crystal X-ray diffraction

Back to Top