Artery-vein separation of human vasculature from 3D thoracic CT angio scans

This paper presents vascular tree reconstruction and artery-vein separation methods from 3D thoracic CT-angiography (CTA) images. In the methods, the lungs, blood vessels and the heart are segmented by using intensity-based thresholds and morphological operations. After the distance transform for the regions of blood vessels and the heart, we compute seed points that are the maxima of distance values. At each seed point, spheres are inflated until hit a boundary. The spheres and the connections between overlapped spheres make a graph representation of the 3D image. Once the pulmonary trunk is detected by using directions in the graph, blood vessels are traversed toward the heart, while merging and verifying branches. If a branch is linked to the pulmonary trunk, then all subsegmental trees of the branch are classified into pulmonary arteries. Otherwise, it is a pulmonary vein.

[1]  Milan Sonka,et al.  Highly automated segmentation of arterial and venous trees from three-dimensional magnetic resonance angiography (MRA) , 2004, The International Journal of Cardiovascular Imaging.

[2]  P. Molina.  Spiral CT in the diagnosis of pulmonary embolism , 2001 .

[3]  L. Schwartz,et al.  Automatic detection of small lung nodules on CT utilizing a local density maximum algorithm , 2003, Journal of applied clinical medical physics.

[4]  Robert M. Haralick,et al.  Recursive erosion, dilation, opening, and closing transforms , 1995, IEEE Trans. Image Process..

[5]  Francis K. H. Quek,et al.  A review of vessel extraction techniques and algorithms , 2004, CSUR.

[6]  David P. Naidich,et al.  Analysis of arterial subtrees affected by pulmonary emboli , 2004, SPIE Medical Imaging.

[7]  Gady Agam,et al.  Vessel tree reconstruction in thoracic CT scans with application to nodule detection , 2005, IEEE Transactions on Medical Imaging.

[8]  Jun-ichiro Toriwaki,et al.  New algorithms for euclidean distance transformation of an n-dimensional digitized picture with applications , 1994, Pattern Recognit..

[9]  Eric A. Hoffman,et al.  Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images , 2001, IEEE Transactions on Medical Imaging.

[10]  Cristian Lorenz,et al.  Automatic extraction of the pulmonary artery tree from multi-slice CT data , 2005, SPIE Medical Imaging.

[11]  U Joseph Schoepf,et al.  CT angiography for diagnosis of pulmonary embolism: state of the art. , 2004, Radiology.

[12]  Xujiong Ye,et al.  An accurate and reproducible scheme for quantification of coronary artery calcification in CT scans , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  Mie Sato,et al.  Penalized-Distance Volumetric Skeleton Algorithm , 2001, IEEE Trans. Vis. Comput. Graph..

[14]  Max A. Viergever,et al.  Level-set-based artery-vein separation in blood pool agent CE-MR angiograms , 2003, IEEE Transactions on Medical Imaging.

[15]  Jayaram K. Udupa,et al.  Artery-vein separation via MRA-An image processing approach , 2001, IEEE Transactions on Medical Imaging.

[16]  S. Armato,et al.  Automated lung segmentation for thoracic CT impact on computer-aided diagnosis. , 2004, Academic radiology.

[17]  Kunio Doi,et al.  Computerized detection of pulmonary embolism in spiral CT angiography based on volumetric image analysis , 2002, IEEE Transactions on Medical Imaging.

[18]  Katja Bühler,et al.  Geometric Methods for Vessel Visualization and Quantification — A Survey , 2004 .

[19]  Bram van Ginneken,et al.  Computer analysis of computed tomography scans of the lung: a survey , 2006, IEEE Transactions on Medical Imaging.

[20]  L R Schad,et al.  Separation of arteries and veins in 3D MR angiography using correlation analysis , 2000, Magnetic resonance in medicine.