A Novel Segmentation Algorithm for Digital Subtraction Angiography Images: First Experimental Results

We present an efficient algorithm for vessel segmentation of Digital Subtraction Angiography (DSA) images. Continuous DSA images (projections), obtained by X-ray fluoroscopy with contrast-media, are normally used as road maps in vessel catheterization. A more efficient technique would consist in the use of a 3D model reconstruction of the vascular tree, instead of continuous X-ray scans, as a map. By separating vessel information from the undesired background (noise and signals coming from other organs and motion artefacts), efficient segmentation can play a key role in reducing the number of projections (X-ray scans) necessary to reconstruct a 3D vascular model. In what follows, the proposed method is described and some experimental results are reported, thus illustrating the behaviour of the algorithm when compared to other segmentation methods, ideated for the same application. The automatic calculation methods for the parameters used are also reported and discussed.

[1]  Wiro J. Niessen,et al.  Level set based cerebral vasculature segmentation and diameter quantification in CT angiography , 2006, Medical Image Anal..

[2]  Eugenio Picano,et al.  Informed consent and communication of risk from radiological and nuclear medicine examinations: how to escape from a communication inferno , 2004, BMJ : British Medical Journal.

[3]  Joachim Hornegger,et al.  Semi-automatic level-set based segmentation and stenosis quantification of the internal carotid artery in 3D CTA data sets , 2007, Medical Image Anal..

[4]  Demetri Terzopoulos,et al.  United Snakes , 1999, Medical Image Anal..

[5]  Max A. Viergever,et al.  Retrospective motion correction in digital subtraction angiography: a review , 1999, IEEE Transactions on Medical Imaging.

[6]  Anil A. Bharath,et al.  Segmentation of blood vessels from red-free and fluorescein retinal images , 2007, Medical Image Anal..

[7]  Roberto Marcondes Cesar Junior,et al.  Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification , 2005, IEEE Transactions on Medical Imaging.

[8]  Tianxu Zhang,et al.  Knowledge-based adaptive thresholding segmentation of digital subtraction angiography images , 2007, Image Vis. Comput..

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

[10]  G. Placidi,et al.  Theory of Adaptive Acquisition Method for Image Reconstruction from Projections and Application to EPR Imaging , 1995 .

[11]  Albert C. S. Chung.  Image Segmentation Methods for Detecting Blood Vessels in Angiography , 2006, 2006 9th International Conference on Control, Automation, Robotics and Vision.

[12]  Giuseppe Placidi,et al.  Angular Space-Domain Interpolation for Filtered Back Projection Applied to Regular and Adaptively Measured Projections , 1996 .

[13]  Giuseppe Placidi,et al.  Development of an auxiliary system for the execution of vascular catheter interventions with a reduced radiological risk; system description and first experimental results , 2007, Comput. Methods Programs Biomed..

[14]  Max A. Viergever,et al.  Vessel enhancing diffusion: A scale space representation of vessel structures , 2006, Medical Image Anal..

[15]  F Buchmann,et al.  Digital subtraction angiography: fundamental noise characteristics. , 1984, Radiology.

[16]  Nicolas Passat,et al.  Magnetic resonance angiography: From anatomical knowledge modeling to vessel segmentation , 2006, Medical Image Anal..

[17]  Ana Maria Mendonça,et al.  Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction , 2006, IEEE Transactions on Medical Imaging.