Skip to main content

Advertisement

SpringerLink
Log in

Automatic segmentation, detection and quantification of coronary artery stenoses on CTA

  • Original paper
  • Published:
The International Journal of Cardiovascular Imaging Aims and scope Submit manuscript

Abstract

Accurate detection and quantification of coronary artery stenoses is an essential requirement for treatment planning of patients with suspected coronary artery disease. We present a method to automatically detect and quantify coronary artery stenoses in computed tomography coronary angiography. First, centerlines are extracted using a two-point minimum cost path approach and a subsequent refinement step. The resulting centerlines are used as an initialization for lumen segmentation, performed using graph cuts. Then, the expected diameter of the healthy lumen is estimated by applying robust kernel regression to the coronary artery lumen diameter profile. Finally, stenoses are detected and quantified by computing the difference between estimated and expected diameter profiles. We evaluated our method using the data provided in the Coronary Artery Stenoses Detection and Quantification Evaluation Framework. Using 30 testing datasets, the method achieved a detection sensitivity of 29 % and a positive predictive value (PPV) of 24 % as compared to quantitative coronary angiography (QCA), and a sensitivity of 21 % and a PPV of 23 % as compared manual assessment based on consensus reading of CTA by 3 observers. The stenoses degree was estimated with an absolute average difference of 31 %, a root mean square difference of 39.3 % when compared to QCA, and a weighted kappa value of 0.29 when compared to CTA. A Dice of 68 and 65 % was reported for lumen segmentation of healthy and diseased vessel segments respectively. According to the ranking of the evaluation framework, our method finished fourth for stenosis detection, second for stenosis quantification and second for lumen segmentation.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. WHO (2011) Cardiovascular diseases, fact sheet 317. World Health Organization

  2. Roger V, Go A, Lloyd-Jones D, Benjamin E, Berry J. Borden, W., Bravata D, Dai S, Ford E, Fox C et al (2012) Heart disease and stroke statistics2012 update a report from the american heart association. Circulation 125(1):e2–e220

    Article  PubMed  Google Scholar 

  3. Fayad Z, Fuster V (2001) Clinical imaging of the high-risk or vulnerable atherosclerotic plaque. Circ Res 89(4):305–316

    Article  PubMed  CAS  Google Scholar 

  4. Weustink A, de Feyter P (2011) The role of multi-slice computed tomography in stable angina management: a current perspective. Neth Heart J 19(7–8):336–343

    Google Scholar 

  5. Miller JM, Rochitte CE, Dewey M, Arbab-Zadeh A, Niinuma H, Gottlieb I, Paul N, Clouse ME, Shapiro EP, Hoe J et al (2008) Diagnostic performance of coronary angiography by 64-row CT. New Engl J Med 359(22):2324–2336

    Article  PubMed  CAS  Google Scholar 

  6. Pugliese F, Hunink M, Gruszczynska K, Alberghina F, Malagó R, van Pelt N, Mollet N, Cademartiri F, Weustink A, Meijboom W et al (2009) Learning curve for coronary CT angiography: what constitutes sufficient training? Radiology 251(2):359–368

    Article  PubMed  Google Scholar 

  7. Melchionna S, Amati G, Bernaschi M, Bisson M, Succi S, Mitsouras D, Rybicki FJ (2013) Risk assessment of atherosclerotic plaques based on global biomechanics. Med Eng Phys 35(9):1290–1297

    Google Scholar 

  8. Min JK, Leipsic J, Pencina MJ, Berman DS, Koo BK, van Mieghem C, Erglis A, Lin FY, Dunning AM, Apruzzese P et al (2012) Diagnostic accuracy of fractional flow reserve from anatomic CT angiography. Jama 308(12):1237–1245

    Article  PubMed  CAS  Google Scholar 

  9. Kirişli H, Schaap M, Metz C, Dharampal A, Meijboom W, Papadopoulou S, Dedic A, Nieman K, de Graaf M, Meijs M, Cramer M, Broersen A, Cetin S, Eslami A, Florez-Valencia L, Lor K, Matuszewski B, Melki I, Mohr B, Oksuz I, Shahzad R, Wang C, Kitslaar P, Unal G, Katouzian A, Orkisz M, Chen C, Precioso F, Najman L, Masood S, Unay D, van Vliet L, Moreno R, Goldenberg R, Vucini E, Krestin G, Niessen W, van Walsum T (2013) Standardized evaluation framework for evaluating coronary artery stenosis detection, stenosis quantification and lumen segmentation algorithms in computed tomography angiography. Med Image Anal 17(8):859–876

    Google Scholar 

  10. Arnoldi E, Gebregziabher M, Schoepf U, Goldenberg R, Ramos-Duran L, Zwerner P, Nikolaou K, Reiser M, Costello P, Thilo C (2010) Automated computer-aided stenosis detection at coronary CT angiography: initial experience. Eur Radiol 20(5):1160–1167

    Article  PubMed  Google Scholar 

  11. Halpern E, Halpern D (2011) Diagnosis of coronary stenosis with CT angiography: comparison of automated computer diagnosis with expert readings. Acad Radiol 18(3):324–333

    Article  PubMed  Google Scholar 

  12. Khan M, Wesarg S, Gurung J, Dogan S, Maataoui A, Brehmer B, Herzog C, Ackermann H, Aßmus B, Vogl, T (2006) Facilitating coronary artery evaluation in MDCT using a 3D automatic vessel segmentation tool. Eur Radiol 16(8):1789–1795

    Article  PubMed  Google Scholar 

  13. Kelm B, Mittal S, Zheng Y, Tsymbal A, Bernhardt D, Vega-Higuera F, Zhou S, Meer P, Comaniciu D (2011) Detection, grading and classification of coronary stenoses in computed tomography angiography. Medical Image Computing and Computer-Assisted Intervention—MICCAI, pp 25–32

  14. Wesarg S, Khan M, Firle E (2006) Localizing calcifications in cardiac CT data sets using a new vessel segmentation approach. J Digit Imaging 19(3):249–257

    Article  PubMed  Google Scholar 

  15. Xu Y, Liang G, Hu G, Yang Y, Geng J, Saha P (2012) Quantification of coronary arterial stenoses in CTA using fuzzy distance transform. Comput Med Imaging Graph 36(1):11–24

    Article  PubMed  Google Scholar 

  16. Saur S, Alkadhi H, Desbiolles L, Székely G, Cattin P (2008) Automatic detection of calcified coronary plaques in computed tomography data sets. Medical Image Computing and Computer-Assisted Intervention—MICCAI, pp 170–177

  17. Tessmann M, Vega-Higuera F, Fritz D, Scheuering M, Greiner G (2009) Multi-scale feature extraction for learning-based classification of coronary artery stenosis. In: SPIE medical imaging, International Society for Optics and Photonics, pp 726002–726002

  18. Zuluaga MA, Magnin IE, Hoyos MH, Leyton EJD, Lozano F, Orkisz M (2011) Automatic detection of abnormal vascular cross-sections based on density level detection and support vector machines. Int J Comput Assist Radiol Surg 6(2):163–174

    Article  PubMed  Google Scholar 

  19. Agatston A, Janowitz W, Hildner F, Zusmer N, Viamonte Jr M, Detrano R (1990) Quantification of coronary artery calcium using ultrafast computed tomography. J Am Coll Cardiol 15(4):827

    Article  PubMed  CAS  Google Scholar 

  20. Metz C, Schaap M, Weustink A, Mollet N, van Walsum T, Niessen W (2009) Coronary centerline extraction from ct coronary angiography images using a minimum cost path approach. Med Phys 36(12):5568–5579

    Article  PubMed  CAS  Google Scholar 

  21. Frangi A, Niessen W, Vincken K, Viergever M (1998) Multiscale vessel enhancement filtering. Medical Image Computing and Computer-Assisted Intervention—MICCAI, pp 130–137

  22. Rybicki FJ, Otero HJ, Steigner ML, Vorobiof G, Nallamshetty L, Mitsouras D, Ersoy H, Mather RT, Judy PF, Cai T et al (2008) Initial evaluation of coronary images from 320-detector row computed tomography. Int J Cardiovasc Imaging 24(5):535–546

    Article  PubMed  Google Scholar 

  23. Steigner ML, Mitsouras D, Whitmore AG, Otero HJ, Wang C, Buckley O, Levit NA, Hussain AZ, Cai T, Mather RT et al. (2010) Iodinated contrast opacification gradients in normal coronary arteries imaged with prospectively ECG-gated single heart beat 320-detector row computed tomography. Circ Cardiovasc Imaging 3(2):179–186

    Article  PubMed  Google Scholar 

  24. Tang H, Walsum T, van Onkelen RS, Hameeteman R, Klein S, Schaap M, Tori FL, van den Bouwhuijsen QJ, Witteman J, der Lugt A et al. (2012) Semiautomatic carotid lumen segmentation for quantification of lumen geometry in multispectral MRI. Med Image Anal 16:1201–1215

    Google Scholar 

  25. Gülsün MA, Tek H (2008) Robust vessel tree modeling. In: Medical Image Computing and Computer-Assisted Interventation—MICCAI, Springer, pp 602–611

  26. Carreira-Perpinan M (2007) Gaussian mean-shift is an EM algorithm. Pattern Anal Mach Intell IEEE Trans 29(5):767–776

    Article  Google Scholar 

  27. van Walsum T, Schaap M, Metz C, van der Giessen A, Niessen W (2008) Averaging centerlines: mean shift on paths. Medical Image Computing and Computer-Assisted Intervention—MICCAI, pp 900–907

  28. Dijkstra E (1959) A note on two problems in connexion with graphs. Numerische mathematik 1(1):269–271

    Article  Google Scholar 

  29. Schaap M, Neefjes L, Metz C, van der Giessen A, Weustink A, Mollet N, Wentzel J, van Walsum T, Niessen W (2009) Coronary lumen segmentation using graph cuts and robust kernel regression. In: Information processing in medical imaging. Springer, pp 528–539

  30. Debruyne M, Hubert M, Suykens J (2008) Model selection in kernel based regression using the influence function. J Mach Learn Res 9:2377–2400

    Google Scholar 

  31. Shahzad R, van Walsum T, Kirişli H, Tang H, Metz C, Schaap M, van Vliet L, Niessen W (2012) Automatic detection, quantification and lumen segmentation of the coronary arteries using two-point centerline extraction scheme. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

  32. Shahzad R, Schaap M, van Walsum T, Klien S, Weustink AC, van Vliet LJ, Niessen WJ (2010) A patient-specific coronary density estimate. In: Biomedical imaging: from nano to macro, 2010 IEEE international symposium on, IEEE, pp 9–12

  33. Kitamura Y, Li Y, Ito W (2012) Automatic coronary extraction by supervised detection and shape matching. In: Biomedical imaging (ISBI), 2012 9th IEEE international symposium on, IEEE, pp 234–237

  34. Yang G, Kitslaar P, Frenay M, Broersen A, Boogers MJ, Bax JJ, Reiber JH, Dijkstra J (2012) Automatic centerline extraction of coronary arteries in coronary computed tomographic angiography. Int J Cardiovasc Imaging 28(4):921–933

    Article  PubMed  Google Scholar 

  35. Goldenberg R, Eilot D, Begelman G, Walach E, Ben-Ishai E, Peled N (2012) Computer-aided simple triage (CAST) for coronary CT angiography (CCTA). Int J Comput Assist Radiol Surg 7(6):819–827

    Article  PubMed  Google Scholar 

  36. Zambal S, Hladuvka J, Kanitsar A, Bühler K (2008) Shape and appearance models for automatic coronary artery tracking. Insight J 4:1–8

    Google Scholar 

  37. Duval M, Ouzeau E, Precioso F, Matuszewski B (2012) Coronary artery stenoses detection with random forest. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

  38. Cetin S, Unal G (2012) Automatic detection of coronary artery stenosis in CTA based on vessel intensity and geometric features. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

  39. Broersen A, Kitslaar P, Frenay M, Dijkstra J (2012) FrenchCoast: fast, robust extraction for the nice challenge on coronary artery segmentation of the tree. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

  40. Flórez Valencia L, Orkisz M, Corredor Jerez, RA, Torres González JS, Correa Agudelo EM, Mouton C, Hernández Hoyos M (2012) Coronary artery segmentation and stenosis quantification in CT images with use of a right generalized cylinder model. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

  41. Mohr B, Masood S, Plakas C (2012) Accurate stenosis detection and quantification in coronary CTA. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

  42. Öksüz d, Ünay D, Kadipaşaoğlu K (2012) A hybrid method for coronary artery stenosis detection and quantification. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

  43. Eslami A, Aboee A, Hodaei Z, Moghaddam MJ, Carlier S, Katouzian A, Navab N (2012) Quantification of coronary arterial stenosis by inflating tubes in CTA images. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

  44. Wang C, Moreno R, Smedby Ö (2012) Vessel segmentation using implicit model-guided level sets. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

  45. Lor K, Chen C (2012) Probabilistic model based evaluation of coronary artery stenosis on CTA. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

  46. Melki I, Talbot H, Cousty J, Pruvot C, Knoplioch J, Launay L, Najman L (2012) Automatic coronary arteries stenoses detection in 3D CTA. In: Proceedings of MICCAI workshop "3D cardiovascular imaging: a MICCAI segmentation challenge"

Download references

Acknowledgments

This work is supported by a grant from the Dutch Ministry of Economic Affairs (AgentschapNL) under the title "Het Hart in Drie Dimensies" (PID06003). Medical Delta: Pieken in de Delta.

Conflict of interest

None.

Author information

Author notes

  1. Michiel Schaap

    Present address: HeartFlow, Inc., Redwood City, CA, USA

Authors and Affiliations

  1. Quantitative Imaging Group, Department of Imaging Science and Technology, Faculty of Applied Science, Delft University of Technology, Delft, The Netherlands

    Rahil Shahzad, Hui Tang, Lucas van Vliet & Wiro Niessen

  2. Biomedical Imaging Group Rotterdam, Department of Radiology and Medical Informatics, Erasmus MC, Rotterdam, The Netherlands

    Rahil Shahzad, Hortense Kirişli, Coert Metz, Hui Tang, Michiel Schaap, Wiro Niessen & Theo van Walsum

Authors
  1. Rahil Shahzad
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hortense Kirişli
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Coert Metz
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hui Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Michiel Schaap
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Lucas van Vliet
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Wiro Niessen
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Theo van Walsum
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rahil Shahzad.

Additional information

Rahil Shahzad and Hortense Kirişli contributed equally to this research.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Shahzad, R., Kirişli, H., Metz, C. et al. Automatic segmentation, detection and quantification of coronary artery stenoses on CTA. Int J Cardiovasc Imaging 29, 1847–1859 (2013). https://doi.org/10.1007/s10554-013-0271-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10554-013-0271-1

Keywords

Search

Navigation