Advertisement

A supervised classification-based method for coronary calcium detection in non-contrast CT

  • Uday Kurkure
  • Deepak R. Chittajallu
  • Gerd Brunner
  • Yen H. Le
  • Ioannis A. Kakadiaris
Original Paper

Abstract

Accurate quantification of coronary artery calcium provides an opportunity to assess the extent of atherosclerosis disease. Coronary calcification burden has been reported to be associated with cardiovascular risk. Currently, an observer has to identify the coronary calcifications among a set of candidate regions, obtained by thresholding and connected component labeling, by clicking on them. To relieve the observer of such a labor-intensive task, an automated tool is needed that can detect and quantify the coronary calcifications. However, the diverse and heterogeneous nature of the candidate regions poses a significant challenge. In this paper, we investigate a supervised classification-based approach to distinguish the coronary calcifications from all the candidate regions and propose a two-stage, hierarchical classifier for automated coronary calcium detection. At each stage, we learn an ensemble of classifiers where each classifier is a cost-sensitive learner trained on a distinct asymmetrically sampled data subset. We compute the relative location of the calcifications with respect to a heart-centered coordinate system, and also use the neighboring regions of the calcifications to better characterize their properties for discrimination. Our method detected coronary calcifications with an accuracy, sensitivity and specificity of 98.27, 92.07 and 98.62%, respectively, for a testing dataset of non-contrast computed tomography scans from 105 subjects.

keywords

Computed tomography Coronary calcium Supervised classification 

Notes

Acknowledgments

This work was supported in part by NSF Grants IIS-0431144 and CNS-0521527.

References

  1. 1.
    National Institutes of Health (2007) Disease statistics. National Heart Lung and Blood Institute, Technical reportGoogle Scholar
  2. 2.
    Greenland P, LaBree L, Azen S, Doherty T, Detrano R (2004) Coronary artery calcium score combined with Framingham score for risk prediction in asymptomatic individuals. J Am Med Assoc 291(2):210–215CrossRefGoogle Scholar
  3. 3.
    Shaw L, Raggi P, Schisterman E, Berman D, Callister T (2003) Prognostic value of cardiac risk factors and coronary artery calcium screening for all-cause mortality. Radiology 228(3):826–833CrossRefPubMedGoogle Scholar
  4. 4.
    Taylor A, Bindeman J, Feuerstein I, Cao F, Brazaitis M, O’Malley P (2005) Coronary calcium independently predicts incident premature coronary heart disease over measured cardiovascular risk factors: mean three-year outcomes in the prospective army coronary calcium (PACC) project. J Am Coll Cardiol 46(5):807–814CrossRefPubMedGoogle Scholar
  5. 5.
    Wong ND, Budoff MJ, Pio J, Detrano RC (2002) Coronary calcium and cardiovascular event risk: evaluation by age- and sex-specific quartiles. Am Heart J 143(3):456–459CrossRefPubMedGoogle Scholar
  6. 6.
    Edvardsen T, Detrano R, Rosen B, Carr J, Liu K, Lai S, Shea S, Pan L, Bluemke D, Lima J (2006) Coronary artery atherosclerosis is related to reduced regional left ventricular function in individuals without history of clinical cardiovascular disease: the multi-ethnic study of atherosclerosis. Arterioscler Thromb Vasc Biol 26(1):206–211CrossRefPubMedGoogle Scholar
  7. 7.
    Rumberger J, Kaufman L (2003) A rosetta stone for coronary calcium risk stratification: agatston, volume, and mass scores in 11,490 individuals. Am J Roentgenol 181(3):743–748Google Scholar
  8. 8.
    Ukai Y, Niki N, Satoh H, Watanabe S, Ohmatsu H, Eguchi K, Moriyama N (1996) An algorithm for coronary calcification diagnosis based on helical CT images. In: Proceedings of International conference on pattern recognition, vol. 3. Washington, DC, pp 543–547Google Scholar
  9. 9.
    Ukai Y, Niki N, Satoh H, Watanabe S, Ohmatsu H, Eguchi K, Moriyama N (1998) A coronary calcification diagnosis system based on helical CT images. IEEE Trans Nucl Sci 45(6):3083–3088CrossRefGoogle Scholar
  10. 10.
    Isgum I, Rutten A, Prokop M, van Ginneken B (2007) Detection of coronary calcifications from computed tomography scans for automated risk assessment of coronary artery disease. Med Phys 34(4):1450–1461CrossRefPubMedGoogle Scholar
  11. 11.
    Kurkure U, Chittajallu D, Brunner G, Yalamanchili R, Kakadiaris I (2008) Detection of coronary calcifications using supervised hierarchical classification. In: Proceedings of medical image computing and computer-assisted intervention workshop on computer vision for intravascular and intracardiac imaging. New York, NYGoogle Scholar
  12. 12.
    Hu S, Hoffman E, Reinhardt J (2001) Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images. IEEE Trans Med Imaging 20(6):490–498CrossRefPubMedGoogle Scholar
  13. 13.
    Laws K (1980) Texture image segmentation. Ph.D. dissertation, University of Southern CaliforniaGoogle Scholar
  14. 14.
    Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3:610–621CrossRefGoogle Scholar
  15. 15.
    Peng H, Long F, Ding C (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27(8):1226–1238CrossRefPubMedGoogle Scholar
  16. 16.
    Vapnik V (1998) Statistical learning theory. Wiley-Interscience, ISBN 0471030031Google Scholar
  17. 17.
    Osuna E, Freund R, Girosi F (1997) Support vector machines: training and applications. Massachusetts Institute of Technology, Technical Report AIM-1602, [Online]. Available: http://www.dspace.mit.edu/handle/1721.1/7290
  18. 18.
    Hsu C, Chang C, Lin C (2003) A practical guide to support vector classification. National Taiwan University, Technical reportGoogle Scholar
  19. 19.
    Chang C-C, Lin C-J (2001) LIBSVM: a library for support vector machines. Software available at http://www.csie.ntu.edu.tw/
  20. 20.
    Brunner G, Chittajallu D, Kurkure U, Kakadiaris I (2008) A heart-centered coordinate system for the detection of coronary artery zones in non-contrast computed tomography data. In: Proceedings of medical image computing and computer-assisted intervention workshop on computer vision for intravascular and intracardiac imaging. New York, NYGoogle Scholar
  21. 21.
    Brunner G, Chittajallu D, Kurkure U, Kakadiaris I (2010) Toward the automatic detection of coronary artery calcification in non-contrast computed tomography data. Int J Cardiovasc Imaging (in press)Google Scholar
  22. 22.
    Wu J, Brubaker S, Mullin M, Rehg J (2008) Fast asymmetric learning for cascade face detection. IEEE Trans Pattern Anal Mach Intell 30(3):369–382CrossRefPubMedGoogle Scholar
  23. 23.
    Yan S, Li M, Zhang H, Cheng Q (2003) Ranking prior likelihood distributions for bayesian shape localization framework. In: Proceedings of IEEE international conference on computer vision, pp 51–58Google Scholar
  24. 24.
    Dietterich T (2000) Ensemble methods in machine learning. Lect Notes Comput Sci 1857:1–15 [Online]. Available: http://citeseer.ist.psu.edu/dietterich00ensemble.html
  25. 25.
    Rosito G, Massaro J, Hoffmann U, Ruberg F, Mahabadi A, Vasan R, O’Donnell C, Fox C (2008) Pericardial fat, visceral abdominal fat, cardiovascular disease risk factors, and vascular calcification in a community-based sample: the Framingham heart study. Circulation 117(5):605–613 [Online]. Available: http://www.circ.ahajournals.org/cgi/content/abstract/117/5/605 Google Scholar
  26. 26.
    Rodondi N, Taylor BC, Bauer DC, Lui LY, Vogt MT, Fink HA, Browner WS, Cummings SR, Ensrud KE (2007) Association between aortic calcification and total and cardiovascular mortality in older women. J Intern Med 261(3):238–244CrossRefPubMedGoogle Scholar
  27. 27.
    Witteman JC, Kok FJ, van Saase JL, Valkenburg HA (1986) Aortic calcification as a predictor of cardiovascular mortality. Lancet 2(8516):1120–1122CrossRefPubMedGoogle Scholar
  28. 28.
    Brown E, Kronmal R, Bluemke D, Guerci A, Carr J, Goldin J, Detrano R (2008) Coronary calcium coverage score: determination, correlates, and predictive accuracy in the multi-ethnic study of atherosclerosis. Radiology 247:669–675CrossRefPubMedGoogle Scholar
  29. 29.
    Kakadiaris I, Kurkure U, Bandekar A, O’Malley S, Naghavi M (2010) Cardiovascular informatics. In: Paragios N, Ayache N, Duncan J (eds) Handbook of biomedical imaging. Springer, Berlin (in press)Google Scholar
  30. 30.
    Kakadiaris I, Kurkure U, Mendizabal-Ruiz E, Naghavi M (2009) Towards cardiovascular risk stratification using imaging data. In: Proceedings of 31st international conference of the IEEE engineering in medicine and biology society. Minneapolis, MNGoogle Scholar
  31. 31.
    Kakadiaris I, Mendizabal-Ruiz E, Kurkure U, Naghavi M (2009) Challenges and opportunities for extracting cardiovascular risk biomarker from imaging data. In: Proceedings of 14th Iberoamerican congress on pattern recognition. Guadalajara, Mexico, 15–18 November, pp 227–235Google Scholar
  32. 32.
    Chittajallu D, Balanca P, Kakadiaris I (2009) Automatic delineation of the inner thoracic region in non-contrast CT data. In: Proceedings of 31st international conference of the IEEE engineering in medicine and biology society. Minneapolis, MNGoogle Scholar
  33. 33.
    Chittajallu D, Brunner G, Kurkure U, Yalamanchili R, Kakadiaris I (2009) Fuzzy-cuts: a knowledge-driven graph-based method for medical image segmentation. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition. Miami Beach, FLGoogle Scholar
  34. 34.
    Kurkure U, Avila-Montes O, Kakadiaris I (2008) Automated segmentation of thoracic aorta in non-contrast CT images. In: Proceedings of IEEE international symposium on biomedical imaging: from nano to macro. Paris, FranceGoogle Scholar
  35. 35.
    Avila-Montes O, Kurkure U, Kakadiaris I (2010) Aorta segmentation in non-contrast cardiac CT images using an entropy-based cost function. In: Proceedings of society of photographic instrumentation engineers medical imaging conference. SPIE, San Diego, CA, Feb 13–18 (in press)Google Scholar
  36. 36.
    Yalamanchili R, Kurkure U, Dey D, Berman D, Kakadiaris I (2010) Knowledge-based quantification of pericardial fat in non-contrast CT data. In: Proceedings of society of photographic instrumentation engineers medical imaging conference. SPIE, San Diego, CA, Feb 13–18 (in press)Google Scholar

Copyright information

© Springer Science+Business Media, B.V. 2010

Authors and Affiliations

  • Uday Kurkure
    • 1
  • Deepak R. Chittajallu
    • 1
  • Gerd Brunner
    • 1
  • Yen H. Le
    • 1
  • Ioannis A. Kakadiaris
    • 2
  1. 1.Computational Biomedicine Lab, Department of Computer ScienceUniversity of HoustonHoustonUSA
  2. 2.Computational Biomedicine Lab, Departments of Computer Science, Electrical and Computer Engineering and Biomedical EngineeringUniversity of HoustonHoustonUSA

Personalised recommendations