Title :
3D vessel reconstruction from biplane angiograms using snakes
Author :
Radeva, P. ; Toledo, R. ; Von Land, C. ; Villanueva, J.
Author_Institution :
Comput.. Vision Centre, Barcelona, Spain
Abstract :
In this paper, we propose a physics-based model to segment and reconstruct coronary vessels from biplane angiograms. We use the snake technique to model the vessel, the snake deforms in space to adjust its projections to the image data. In this way, segmentation and 3D reconstruction are unified into the same procedure assuring that only plausible vessel shapes will be detected. The method is general allowing to reconstruct the coronary tree from any angles and distances. The results are encouraging
Keywords :
angiocardiography; blood vessels; cardiovascular system; curve fitting; diagnostic radiography; feature extraction; image reconstruction; image representation; image segmentation; medical image processing; 3D curve; 3D vessel reconstruction; B-snake; angiographic images; biplane angiograms; coronary vessels; feature extraction; image segmentation; isocentre position; physics-based model; snake technique; top-down approach; Angiography; Computer vision; Deformable models; Feature extraction; Geometry; Image reconstruction; Image segmentation; Reconstruction algorithms; Shape; X-ray imaging;
Conference_Titel :
Computers in Cardiology 1998
Conference_Location :
Cleveland, OH
Print_ISBN :
0-7803-5200-9
DOI :
10.1109/CIC.1998.731988
