Automatic segmentation of coronary arteries using a multiscale Top-Hat operator and multiobjective optimizationSegmentación automática de arterias coronarias utilizando un operador Top-Hat multiescala y optimización multiobjetivo
Abstract:

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.

Resumen En este artículo se presenta un nuevo método de segmentación de arterias coronarias en imágenes angiográficas de rayos X consistente en dos etapas. En la primera etapa, un operador top-hat multiescala basado en las propiedades de la matriz Hessiana es introducido para realzar estructuras con forma arterial en el angiograma. Los resultados del operador top-hat multiescala propuesto son comparados con métodos multiescala basados en filtros de correspondencia Gaussiana, matriz Hessiana y operadores morfológicos, los cuales son analizados usando el área (Az) bajo la curva característica operativa del receptor. En la segunda etapa, un nuevo método de umbralización basado en optimización multiobjetivo mediante la aproximación de la suma ponderada para clasificar pixeles arteriales y no arteriales es presentado. El desempeño del método multiobjetivo es comparado con siete métodos de umbralización automática utilizando angiogramas delineados por un especialista mediante las medidas de sensibilidad, especificidad y exactitud. Finalmente, el método propuesto es comparado con cinco métodos de segmentación arterial pertenecientes al estado del arte. Los resultados de realzado arterial mediante el operador top-hat multiescala demostraron la mejor exactitud con Az = 0.942 usando un conjunto de entrenamiento de 40 angiogramas y Az = 0.965 con un conjunto de prueba independiente de 40 angiogramas. Los resultados de segmentación de arterias coronarias usando el método de umbralización multiobjetivo proporcionaron un desempeño promedio de 0.923 con el conjunto de prueba de angiogramas.

Keywords:
    • segmentación automática;
    • angiogramas coronarios;
    • matriz Hessiana;
    • umbralización multiobjetivo;
    • realzado arterial;
    • Automatic segmentation;
    • coronary angiograms;
    • Hessian matrix;
    • multiobjective thresholding;
    • vessel enhancement.

References

  • An improved matched filter for blood vessel detection of digital retinal images
    Al-Rawi, M.
    Qutaishat, M.
    Arrar, M.
      Computers in Biology and Medicine 2007 37 262-7
  • Bouraoui, B.
    Ronse, C.
    Baruthio, J.
    Passat, N.
    Germain, P.
      Fully automatic 3D segmentation of coronary arteries based on mathematical morphology 2008 5IEEE International Symposium on Biomedical Imaging (ISBI): From Nano to Macro 1059-62
  • Chanwimaluang, T.
    Fan, G.
      An efficient blood vessel detection algorithm for retinal images using local entropy thresholding 2003 5 IEEE International Symposium on Circuits and Systems 5 21-4
  • Hybrid retinal image registration
    Chanwimaluang, T.
    Fan, G.
    Fransen, S.R.
      IEEE Transactions on Information Technology in Biomedicine 2006 10 1 1 129-42
  • Detection of blood vessels in retinal images using two-dimensional matched filters
    Chaudhuri, S.
    Chatterjee, S.
    Katz, N.
    Nelson, M.
    Goldbaum, M.
      IEEE Transactions on Medical Imaging 1989 8 3 3 263-9
  • Detection of coronary artery tree using morphological operator
    Eiho, S.
    Qian, Y.
      Computers in Cardiology 1997 24 525-8
  • Frangi, A.F.
    Niessen, W.J.
    Vincken, K.L.
    Viergever, M.A.
      Multiscale vessel enhancement filtering 1998 Medical Image Computing and Computer-Assisted Intervention (MICCAI'98) 130-7Springer LNCS
  • Vascular tree segmentation in medical images using Hessian-based multiscale filtering and level set method
    Jin, J.
    Yang, L.
    Zhang, X.
    Ding, M.
      Computational and Mathematical Methods in Medicine 2013
  • Kang, W.
    Kang, W.
    Li, Y.
    Wang, Q.
      The segmentation method of degree-based fusion algorithm for coronary angiograms 2013 2International Conference on Measurement, Information and Control 2013 696-9
  • Kang, W.
    Wang, K.
    Chen, W.
    Kang, W.
      Segmentation method based on fusion algorithm for coronary angiograms 2009 2International Congress on Image and Signal Processing (CISP) 2009 1-4
  • A new method for gray-level picture thresholding using the entropy of the histogram
    Kapur, J.N.
    Sahoo, P.K.
    Wong, A.K.C.
      Computer Vision, Graphics, and Image Processing 1985 29 273-85
  • Threshold selection based on a simple image statistic
    Kittler, J.
    Illingworth, J.
    Föglein, J.
      Computer Vision, Graphics, and Image Processing 1985 30 125-47
  • Lara, D.S.D.
    Faria, A.W.C.
    Araujo, A.A.
    Menotti, D.
      A semi-automatic method for segmentation of the coronary artery tree from angiography 2009 XXIIBrazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI) 194-201
  • Li, Y.
    Zhou, S.
    Wu, J.
    Ma, X.
    Peng, K.
      A novel method of vessel segmentation for X-ray coronary angiography images 2012 urth International Conference on Computational and Information Sciences (ICCIS) 468-71
  • A multi-scale line filter with automatic scale selection based on the Hessian matrix for medical image segmentation
    Lorenz, C.
    Carlsen, I.C.
    Buzug, T.
    Fassnacht, C.
    Weese, J.
      Proc. Scale-Space Theories in Computer Vision 1997 1252 152-63
  • Artery skeleton extraction using topographic and connected component labeling
    Maglaveras, N.
    Haris, K.
    Efstratiadis, S.N.
    Gourassas, J.
    Louridas, G.
      Computers in Cardiology 2001 28 17-20
  • The weighted sum method for multi-objective optimization: new insights
    Marler, R. T.
    Arora, J. S.
      Structural and Multidisciplinary Optimization 2010 41 853-62
  • M'hiri, F.
    Duong, L.
    Desrosiers, C.
    Cheriet, M.
      Vesselwalker: coronary arteries segmentation using random walks and Hessian-based vesselness filter 2013 IEEE 10th International Symposium on Biomedical Imaging (ISBI): From Nano to Macro 918-21
  • A threshold selection method from gray-level histograms
    Otsu, N.
      IEEE Transactions on Systems, Man, and Cybernetics 1979 9 1 1 62-6
  • Entropic thresholding
    Pal, N. R.
    Pal, S. K.
      Signal Processing 1989 16 97-108
  • Automatic extraction of coronary artery tree on coronary angiograms by morphological operators
    Qian, Y.
    Eiho, S.
    Sugimoto, N.
    Fujita, M.
      Computers in Cardiology 1998 25 765-8
  • Picture thresholding using an iterative selection method
    Ridler, T.W.
    Calvard, S.
      IEEE Transactions on Systems, Man, and Cybernetics 1978 8 630-2
  • Histogram concavity analysis as an aid in threshold selection
    Rosenfeld, A.
    De la Torre, P.
      IEEE Transactions on Systems, Man, and Cybernetics 1983 13 231-5
  • Salem, N.
    Nandi, A.K.
      Unsupervised segmentation of retinal blood vessels using a single parameter vesselness measure 2008 Sixth Indian Conference on Computer Vision, Graphics and Image Processing 528-34
  • Serra, J.
      Image analysis and mathematical morphology 1982 New York Academic Press
  • Tsai, T.C.
    Lee, H.J.
    Chen, M.Y.C.
      Adaptive segmentation of vessels from coronary angiograms using multi-scale filtering 2013 International Conference on Signal-Image Technology and Internet-Based Systems 2013 143-7
  • Moment-preserving thresholding: A new approach
    Tsai, W.H.
      Computer Vision, Graphics, and Image Processing 1985 29 377-93
  • Wang, S.
    Li, B.
    Zhou, S.
      A segmentation method of coronary angiograms based on multi-scale filtering and region-growing 2012 International Conference on Biomedical Engineering and Biotechnology 2012 678-81
  • Automatic vasculature identification in coronary angiograms by adaptive geometrical tracking
    Xiao, R.
    Yang, J.
    Goyal, M.
    Liu, Y.
    Wang, Y.
      Computational and Mathematical Methods in Medicine 2013
History:
  • » pub: 00/00/2015» Digital publication: 00/00/2015

Refbacks

  • There are currently no refbacks.


Copyright (c) 2015 Nova Scientia

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Scope

Nova Scientia is a multidisciplinary, electronic publication that publishes twice a year in the months of May and November; it is published by the Universidad De La Salle Bajío and aims to distribute unpublished and original papers from the different scientific disciplines written by national and international researchers and academics. It does not publish reviews, bibliographical revisions, or professional applications.

Nova Scientia, year 12, issue 24, May – October 2020, is a biannual journal printed by the Universidad De La Salle Bajío, with its address: Av. Universidad 602, Col. Lomas del Campestre, C. P. 37150, León, Gto. México. Phone: (52) 477 214 3900, http://novascientia.delasalle.edu.mx/. Chief editor: Ph.D. Ramiro Rico Martínez. ISSN 2007 - 0705. Copyright for exclusive use No. 04-2008-092518225500/102, Diffusion rights via computer net 04 - 2008 – 121011584800-203 both granted by the Instituto Nacional del Derecho de Autor.

Editor responsible for updating this issue: Direction of Research Department of the Universidad De La Salle Bajío, last updated on May 15th, 2020.