hrcak mascot   Srce   HID

Original scientific paper

Segmentation of Coronary Arteries using Radial Basis Function Neural-Network

Alok Sarwal ; Lockheed Martin Corp., Denver, USA
Atam P. Dhawan ; Department of Bioengineering, University of Toledo, Toledo, USA

Fulltext: english, pdf (7 MB) pages 135-148 downloads: 56* cite
APA 6th Edition
Sarwal, A. & Dhawan, A.P. (1998). Segmentation of Coronary Arteries using Radial Basis Function Neural-Network. Journal of computing and information technology, 6 (2), 135-148. Retrieved from https://hrcak.srce.hr/150230
MLA 8th Edition
Sarwal, Alok and Atam P. Dhawan. "Segmentation of Coronary Arteries using Radial Basis Function Neural-Network." Journal of computing and information technology, vol. 6, no. 2, 1998, pp. 135-148. https://hrcak.srce.hr/150230. Accessed 23 Nov. 2019.
Chicago 17th Edition
Sarwal, Alok and Atam P. Dhawan. "Segmentation of Coronary Arteries using Radial Basis Function Neural-Network." Journal of computing and information technology 6, no. 2 (1998): 135-148. https://hrcak.srce.hr/150230
Harvard
Sarwal, A., and Dhawan, A.P. (1998). 'Segmentation of Coronary Arteries using Radial Basis Function Neural-Network', Journal of computing and information technology, 6(2), pp. 135-148. Available at: https://hrcak.srce.hr/150230 (Accessed 23 November 2019)
Vancouver
Sarwal A, Dhawan AP. Segmentation of Coronary Arteries using Radial Basis Function Neural-Network. Journal of computing and information technology [Internet]. 1998 [cited 2019 November 23];6(2):135-148. Available from: https://hrcak.srce.hr/150230
IEEE
A. Sarwal and A.P. Dhawan, "Segmentation of Coronary Arteries using Radial Basis Function Neural-Network", Journal of computing and information technology, vol.6, no. 2, pp. 135-148, 1998. [Online]. Available: https://hrcak.srce.hr/150230. [Accessed: 23 November 2019]

Abstracts
Biplane and digital subtraction angiography (DSA) have brought about important advances in the diagnosis and treatment of cardiovascular anomalies by allowing for blood flow measurements, estimation of the regional wall stress and study of myocardium motion. Segmentation of the coronary arteries is a critical first step towards an automated interpretation of angiographs. We present an analysis of neural network methods based on a Radial Basis Function (RBF) and back-propagation (BP) network applied to segmentation of the coronary arterial tree. The results of the neural network based segmentation are compared with segmentation techniques based on a delineation algorithm. Features like vessel diameter and centerline coordinates are extracted for segmented images and compared for the various segmentation methods. The network methods are based on first evaluating the best number of cluster partitions and then automatically obtaining the vectors for training. The pixel gray-level values in a small neighborhood along with information of ridges are utilized to provide the training vectors. The ridge locations indicate high likelihood of continuous points on the artery. A discussion of the learning and generalization characteristics for segmentation, by the networks, is presented for multi-view DSA images and tube phantom simulations.

Keywords
segmentation of coronary arteries; Radial Basis Function (RBF) Neural-Network

Hrčak ID: 150230

URI
https://hrcak.srce.hr/150230

Visits: 84 *