Automatic segmentation of coronary arteries using a multiscale Top-Hat operator and multiobjective optimization.
DOI:
https://doi.org/10.21640/ns.v7i15.362Keywords:
Automatic segmentation, coronary angiograms, Hessian matrix, multiobjective thresholding, vessel enhancement.Abstract
This paper presents a new coronary artery segmentation method in X-ray angiographic images consisting of two stages. In the first stage, a multiscale top-hat operator based on the properties of the Hessian matrix is introduced to enhance vessel-like structures in the angiogram. The results of the proposed multiscale top-hat operator are compared with multiscale methods based on Gaussian matched filters, Hessian matrix and morphological operators, and analyzed using the area ( Az ) under the receiver operating characteristic curve. In the second stage, a new thresholding method based on multiobjective optimization following the weighted sum approach to classify vessel and nonvessel pixels is presented. The performance of the multiobjective method is compared with seven automatic thresholding methods using the ground-truth angiograms drawn by a specialist with the sensitivity, specificity and accuracy measures. Finally, the proposed method is compared with five state-of-the-art vessel segmentation methods. The vessel enhancement results using the multiscale top-hat operator demonstrated the highest accuracy with Az = 0.942 with a training set of 40 angiograms and Az = 0.965 with a test set of 40 angiograms. The results of coronary artery segmentation using the multiobjective thresholding method provided an average accuracy performance of 0.923 with the test set of angiograms.
Downloads
References
Al-Rawi M., Qutaishat M. and Arrar M. (2007). An improved matched filter for blood vessel detection of digital retinal images, Computers in Biology and Medicine, (37): p. 262-267.
Chanwimaluang T. and Fan G. (2003). An efficient blood vessel detection algorithm for reti-nal images using local entropy thresholding. Proc. IEEE International Symposium on Circuits and Systems, (5): p. 21-24.
Kang W., Kang W., Li Y., and Wang Q. (2013). The segmentation method of degree-based fusion algorithm for coronary angiograms. 2nd International Conference on Measurement, Information and Control, (2013):p. 696-699.
Marler R. T., and Arora J. S. (2010). The weighted sum method for multi-objective optimiza-tion: new insights. Structural and Multidisciplinary Optimization, (41):p. 853-862.
Tsai T.C., Lee H.J., and Chen M.Y.C. (2013). Adaptive segmentation of vessels from coro-nary angiograms using multi-scale filtering. International Conference on Signal-Image Tech-nology and Internet-Based Systems, (2013):p. 143-147.
Wang S., Li B., and Zhou S. (2012). A segmentation method of coronary angiograms based on multi-scale filtering and region-growing. International Conference on Biomedical Engi-neering and Biotechnology, (2012):p. 678-681.
Xiao R., Yang J., Goyal M., Liu Y., and Wang Y. (2013). Automatic vasculature identifica-tion in coronary angiograms by adaptive geometrical tracking. Computational and Mathemat-ical Methods in Medicine, ID:796342, p. 11.
Published
How to Cite
Issue
Section
License
Copyright (c) 2015 Nova Scientia
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Conditions for the freedom of publication: the journal, due to its scientific nature, must not have political or institutional undertones to groups that are foreign to the original objective of the same, or its mission, so that there is no censorship derived from the rigorous ruling process.
Due to this, the contents of the articles will be the responsibility of the authors, and once published, the considerations made to the same will be sent to the authors so that they resolve any possible controversies regarding their work.
The complete or partial reproduction of the work is authorized as long as the source is cited.
