Hannah Sofian
ABSTRACT
The lumen boundary in the human coronary artery is the contour edge of a blood vessel. The intravascular ultrasound (IVUS) is the medical imaging modality used to view the lumen boundary by the clinicians to detect the coronary artery disease called atherosclerosis. The main problem is to differentiate between the lumen area and the lumen boundary which cannot see clearly. The diameter of the lumen becomes narrowed because of the plaques, lipids and calcium deposits on the artery wall. In this paper, we present the automated segmentation method for detecting the lumen boundary using Otsu threshold, morphological operation and empirical threshold in the IVUS images. We used six types of structured elements to select the best result for automated segmentation of lumen boundary. Forty samples of IVUS images inclusive of the ground truth obtained from the Universitat de Barcelona, Barcelona used in this study. The proposed method segmentation performance measured are Jaccard-Index, Dice Similarity-Index, Hausdorff-Distance, Area Overlapped Error and Percentage Area Difference. The Bland-Altman Plot is used to show the variation between the proposed automatic segmentation area and ground truth area. The structured element of the octagon gave a good result in Hausdorff Distance, and the line gave a better result in Jaccard Index, Percentage Area Distance, Area Overlapped Error, Dice Index and Area Error. The result obtained shows that the segmentation performance of the proposed method is on par with other existing segmentation methods.
- World Health Organization, Cardiovascular diseases (CVDs)Fact sheet No317, Jan 2015. http://www.who.int/mediacentre/factsheets/fs317/en/Google Scholar
- Murray, C.J.L., 2015. Global, regional, and national age-sex specific all-cause and cause-specific mortality for 240 causes of death, 1990--2013: a systematic analysis for the Global Burden of Disease Study 2013. Lancet, vol. 385, no.1, pp117--71, 2015.Google Scholar
- Bestetti, R.B., Restini, C.B.A. and Couto, L.B., 2014. Development of Anatomophysiologic Knowledge Regarding the Cardiovascular System: From Egyptians to Harvey. Arq Bras Cardiol., vol 103, issue 7, pp. 538--545, 2014.Google Scholar
- Tadif, J. C., 2010. Coronary artery disease in 2010. European Heart Journal Supplements, 12 (Supplement C), C2--10, 1093, suq014, 2010.Google Scholar
- Ik, K.J., 2011. Optical Coherence Tomography or Intravascular Ultrasound. JACC: Cardiovascular Interventions, vol. 4 no. 5, 2011.Google Scholar
- Sofiana, H., Mohd Noor, N. and Than, J.C.M., 2015. Detection of the Lumen Boundary in the Coronary Artery Disease. WIE 2015: IEEE International WIE Conference on Electrical and Computer Engineering, Dec 2015.Google Scholar
- Sofianb, H., Mohamad, S., Mohd Noor, N. and Than, J.C.M., 2015. Lumen Coronary Artery Border Detection Using Texture and Chi-square Classification. IVCNZ 2015: The 30th International Conference on Image and Vision Computing New Zealand, Nov 2015.Google Scholar
- Zuo F., 2014. In-body ultrasound image processing for cardiovascular interventions: A review. Neurocomputing, vol. 144, no. 2, pp.38--46, 2014. Google ScholarDigital Library
- Sun, S., Sonka, M., Fellow, IEEE, Beichel, R.R., Members, IEEE, 2013. Graph-Based IVUS Segmentation with Efficient Compute-Aided Refinement. IEEE Transactions on Medical Imaging, vol 32, no.8, pp1636--1549, 2013.Google Scholar
- Mrabti, M.A. and Ali, H.M., 2012. Intravascular Ultrasound Image Segmentation Using Morphological Snakes. I.J. Image, Graphics and Signal Processing, vol. 5, pp54--60, June 2012.Google Scholar
- Jones, J.L., Xie, X. and Essa, E., 2014. Combining region-based and imprecise boundary-based cues for interactive medical imaging segmentation. Int. J. Numer Method Biomed Eng., vol. 30, issue 12, pp. 1649--66, 2014.Google ScholarCross Ref
- Taki, A., Najafi, Z., Rodaki, A., Setarehdan, S.K. and Zoroofi, R.A., 2008. Automatic segmentation of calcified plaques and vessel border in IVUS images. Int. Journal of Computer Assisted Radiology and Surgery, vol 3, issue 3--4, pp347--354, September 2008.Google ScholarCross Ref
- Cardinal, M.H.R., Gilles, S., Tardiff, J.C., Meunier, J., Cloutier, G., 2010. Fast Marching Segmentation of Three-Dimensional Intravascular ultrasound images: A pre- and post-intervention study. Medical Physics vol 37 Issue 7, pp3633--3647, 2010.Google Scholar
- Vard, A., Jamshidi, K. and Movahhedinia, N., 2012. An automated approach for segmentation of intravascular ultrasound images based on parametric contour models. Australia Phys. Eng. Sci. Med., vol 35, issue 2, pp135--150, 2012.Google ScholarCross Ref
- Balocco, S., Gatta, C., Ciompi, F., Wahle, A., Radeva, P., Carlier S., Unal, G., Sanidas, E., Mauri, J., Carillo, X., Kovarnik, T., Wang, C.W., Chen, H.C., Exarchos, T.P., Fotiadis, D.I., Destrempes, Cloutier, F., G., Pujol, O., Alberti, M., Mendizabal-Ruiz, E.G., Rivera, M., Aksoy, T., Downe, R.W., and Kakadiaris, I.A., 2013. Standardized evaluation methodology and reference database for evaluating IVUS image segmentation, Compute Med Imaging, 70--90, Sep 2013.Google Scholar
- Otsu, N. 1979. A Threshold Selection Method from Gray-Level Histograms. IEEE Transaction on Systems, Man, and Cybernetics, vol. SMC-9, no. 1, January 1979.Google Scholar
- Bland, J.M. and Altman, D.G. 1986. Statistical methods for assessing agreement between two methods of clinical measurement. The Lancet, 327(8476), 1986, pp. 307--310.Google ScholarCross Ref
Index Terms
- Lumen boundary detection in IVUS medical imaging using structured element
Recommendations
Automatic IVUS lumen segmentation using a 3D adaptive helix model
AbstractIn this paper, we develop a three dimensional (3D) segmentation algorithm of the lumen visualized using intravascular ultrasound (IVUS) imaging. These images are known for their various granular textures (speckles) that make the ...
Highlights- A simple 3D helical active contour for IVUS image segmentation of the lumen.
- ...
Segmentation of Blood Vessels in Retinal Images Using Multiscale Enhancement
ICECC '12: Proceedings of the 2012 International Conference on Electronics, Communications and ControlAutomated segmentation of retinal vessels in fund us images is first step to assess the vessel features changes. This paper presents a novel method which combines a multiscale vessel measure, morphological operators and Otsu threshold to segment the ...
Combining Growcut and temporal correlation for IVUS lumen segmentation
IbPRIA'11: Proceedings of the 5th Iberian conference on Pattern recognition and image analysisThe assessment of arterial luminal area, performed by IVUS analysis, is a clinical index used to evaluate the degree of coronary artery disease. In this paper we propose a novel approach to automatically segment the vessel lumen, which combines model-...
Comments