06089732

a

06089732 Hachaj, Tomasz Ogiela, Marek R. Segmentation and visualization of tubular structures in computed tomography angiography. Pan, Jeng-Shyang (ed.) et al., Intelligent information and database systems. 4th Asian conference, ACIIDS 2012, Kaohsiung, Taiwan, March 19--21, 2012. Proceedings, Part III. Berlin: Springer (ISBN 978-3-642-28492-2/pbk). Lecture Notes in Computer Science 7198. Lecture Notes in Artificial Intelligence, 495-503 (2012). 2012 Berlin: Springer EN artificial intelligence segmentation of tubular structures computed tomography angiography Hessian matrix Brain stroke

doi:10.1007/978-3-642-28493-9_52

Summary: The new contribution of this article is description of filtering algorithm for detecting tubular structures (veins / arteries) in three-dimensional images. An algorithm incorporate the Frangi's filtration with additional neighborhood analysis filter that eliminates local noises that often remains after that algorithm. The sensitivity of the method is steered by two algorithm's parameters that might be visualized in 3D plot. Changing of those parameters does not require recalculation of filtration results. Also the concepts of those parameters are more intuitive to the potential user then the three scalable eigenvalues -- based Frangi's parameters. The whole solution was tested on real volumetric CTA data.