Skip to main content

Advertisement

SpringerLink
Log in

Machine learning for coronary artery calcification detection and labeling using only native computer tomography

  • Scientific Paper
  • Published:
Physical and Engineering Sciences in Medicine Aims and scope Submit manuscript

Abstract

In recent decades, the World Health Organization has found an increase in the death rate due to cardiovascular disease. Calcifications of the coronary arteries are the main sign of any cardiovascular event. Each individual’s calcium score helps estimate the severity of the disease. However, the score for each artery is more significant. This study aims to research the segmentation, the labeling, and then the complete and partial quantification of calcium using only native coronary computed tomography with the help of machine-learning algorithms. Our semi-automatic system limited the region of interest by applying a defined preprocessing step. We then implemented two random forest classifiers; the first separated true coronary artery calcification (CAC) from the noise, and the second labeled CAC into the right coronary artery, left coronary artery, left anterior descending artery, and left circumflex artery using specific features. Agatston score and volume score of each CAC, each artery, and all of the arteries were calculated. This method gave promising results, comparable to those found in the literature, with the accuracy of 99.98% and 100% for CAC detection and labeling respectively.

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

Similar content being viewed by others

Data availability

The data used in this study were obtained from the orCaScore challenge. The full data can be downloaded from https://orcascore.grand-challenge.org/Home/

Code availability

The code that supported the findings of this study is available on request from the corresponding author (Asmae Mama Zair).

References

  1. Organization WH, et al (2019) World health statistics 2019: monitoring health for the SDGs, sustainable development goals

  2. Litjens G, Ciompi F, Wolterink JM, de Vos BD, Leiner T, Teuwen J et al (2019) State-of-the-art deep learning in cardiovascular image analysis. JACC Cardiovasc Imaging 12(8):1549–1565

    Article  Google Scholar 

  3. Pravina P, Sayaji D, Avinash M et al (2013) Calcium and its role in human body. Int J Res Pharm Biomed Sci 4(2):659–668

    CAS  Google Scholar 

  4. Neves PO, Andrade J, Monção H (2017) Coronary artery calcium score: current status. Radiol Bras 50(3):182–189

    Article  Google Scholar 

  5. Agatston AS, Janowitz WR, Hildner FJ, Zusmer NR, Viamonte M, Detrano R (1990) Quantification of coronary artery calcium using ultrafast computed tomography. J Am Coll Cardiol 15(4):827–832

    Article  CAS  Google Scholar 

  6. Drake R, Vogl AW, Mitchell AW, Tibbitts R, Richardson P (2020) Gray’s atlas of anatomy e-book. Elsevier, Amsterdam

    Google Scholar 

  7. McEvoy JW, Blaha MJ, DeFilippis AP, Budoff MJ, Nasir K, Blumenthal RS et al (2010) Coronary artery calcium progression: an important clinical measurement? A review of published reports. J Am Coll Cardiol 56(20):1613–1622

    Article  Google Scholar 

  8. Santini G, Della Latta D, Martini N, Valvano G, Gori A, Ripoli A, et al (2017) An automatic deep learning approach for coronary artery calcium segmentation. In: EMBEC & NBC 2017, Springer, pp 374–377

  9. Lessmann N, Išgum I, Setio AA, de Vos BD, Ciompi F, de Jong PA, et al (2016) Deep convolutional neural networks for automatic coronary calcium scoring in a screening study with low-dose chest CT. In: Medical imaging 2016: computer-aided diagnosis, vol 9785. International Society for Optics and Photonics. p 978511

  10. Yang G, Chen Y, Sun Q, Ning X, Shu H, Coatrieux JL (2016) Fully automatic coronary calcification detection in non-contrast CT images. Med Phys 43(5):2174–186

    Article  CAS  Google Scholar 

  11. Durlak F, Wels M, Schwemmer C, Sühling M, Steidl S, Maier A (2017) Growing a random forest with fuzzy spatial features for fully automatic artery-specific coronary calcium scoring. In: International workshop on machine learning in medical imaging, Springer, pp 27–35

  12. de Vos BD, Wolterink JM, Leiner T, de Jong PA, Lessmann N, Išgum I (2019) Direct automatic coronary calcium scoring in cardiac and chest CT. IEEE Trans Med Imaging 38(9):2127–2138

    Article  Google Scholar 

  13. Li P, Xu L, Yang L, Wang R, Hsieh J, Sun Z et al (2018) Blooming artifact reduction in coronary artery calcification by a new de-blooming algorithm: initial study. Sci Rep 8(1):1–8

    Google Scholar 

  14. Singh G, Al’Aref SJ, Van Assen M, Kim TS, van Rosendael A, Kolli KK et al (2018) Machine learning in cardiac CT: basic concepts and contemporary data. J Cardiovasc Comput Tomogr 12(3):192–201

    Article  Google Scholar 

  15. Henglin M, Stein G, Hushcha PV, Snoek J, Wiltschko AB, Cheng S (2017) Machine learning approaches in cardiovascular imaging. Circulation 10(10):e005614

    PubMed  Google Scholar 

  16. Siegersma K, Leiner T, Chew D, Appelman Y, Hofstra L, Verjans J (2019) Artificial intelligence in cardiovascular imaging: state of the art and implications for the imaging cardiologist. Netherlands Heart J 1–11

  17. Išgum 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):1450–1461

    Article  Google Scholar 

  18. Kurkure U, Chittajallu DR, Brunner G, Le YH, Kakadiaris IA (2010) A supervised classification-based method for coronary calcium detection in non-contrast CT. Int J Cardiovasc Imaging 26(7):817–828

    Article  Google Scholar 

  19. Xie Y, Cham MD, Henschke C, Yankelevitz D, Reeves AP (2014) Automated coronary artery calcification detection on low-dose chest CT images. In: Medical imaging 2014: computer-aided diagnosis, vol 9035. International Society for Optics and Photonics, p 90350F

  20. Wolterink JM, Leiner T, Takx RA, Viergever MA, Išgum I (2014) An automatic machine learning system for coronary calcium scoring in clinical non-contrast enhanced, ECG-triggered cardiac CT. In: Medical imaging 2014: computer-aided diagnosis, vol 9035. International Society for Optics and Photonics, p 90350E

  21. Wolterink JM, Leiner T, de Vos BD, van Hamersvelt RW, Viergever MA, Išgum I (2016) Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks. Med Image Anal 34:123–136

    Article  Google Scholar 

  22. Lessmann N, van Ginneken B, Zreik M, de Jong PA, de Vos BD, Viergever MA et al (2017) Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions. IEEE Trans Med Imaging 37(2):615–625

    Article  Google Scholar 

  23. Shadmi R, Mazo V, Bregman-Amitai O, Elnekave E (2018) Fully-convolutional deep-learning based system for coronary calcium score prediction from non-contrast chest CT. In: IEEE 15th international symposium on biomedical imaging (ISBI 2018), IEEE, pp 24–28

  24. Šprem J, De Vos BD, Lessmann N, Van Hamersvelt RW, Greuter MJ, De Jong PA et al (2018) Coronary calcium scoring with partial volume correction in anthropomorphic thorax phantom and screening chest CT images. PLoS ONE 13(12):e0209318

    Article  Google Scholar 

  25. Zreik M, Van Hamersvelt RW, Wolterink JM, Leiner T, Viergever MA, Išgum I (2018) A recurrent CNN for automatic detection and classification of coronary artery plaque and stenosis in coronary CT angiography. IEEE Trans Med Imaging 38(7):1588–1598

    Article  Google Scholar 

  26. Zreik M, van Hamersvelt RW, Wolterink JM, Leiner T, Viergever MA, Isgum I (2018) Automatic detection and characterization of coronary artery plaque and stenosis using a recurrent convolutional neural network in coronary CT angiography

  27. Cano-Espinosa C, González G, Washko GR, Cazorla M, Estépar RSJ (2018) On the relevance of the loss function in the Agatston score regression from non-ECG gated CT scans. In: Image analysis for moving organ, breast, and thoracic images, Springer, pp 326–334

  28. Qian Z, Marvasty I, Rinehart S, Voros S (2011) A lesion-specific coronary artery calcium quantification framework for the prediction of cardiac events. IEEE Trans Inf Technol Biomed 15(5):673–680

    Article  Google Scholar 

  29. Isgum I, Prokop M, Niemeijer M, Viergever MA, Van Ginneken B (2012) Automatic coronary calcium scoring in low-dose chest computed tomography. IEEE Trans Med Imaging 31(12):2322–2334

    Article  Google Scholar 

  30. Six O, Quantib B (2018) The ultimate guide to AI in radiology

  31. Christler A, Felföldi E, Mosor M, Sauer D, Walch N, Dürauer A et al (2020) Semi-automation of process analytics reduces operator effect. Bioprocess Biosyst Eng 43(5):753–764

    Article  CAS  Google Scholar 

  32. Buckee GK, Hickman E (1975) A review of automated and semi-automated analysis in brewing. J Inst Brew 81(5):399–407

    Article  CAS  Google Scholar 

  33. Brahim W, Mestiri M, Betrouni N, Hamrouni K (2016) Semi-automated rib cage segmentation in CT images for mesothelioma detection. In: International image processing, applications and systems (IPAS). IEEE, pp 1–6

  34. Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    Article  Google Scholar 

  35. Mohammadi S, Hedjazi A, Sajjadian M, Ghoroubi N, Mohammadi M, Erfani S (2016) Study of the normal heart size in Northwest part of Iranian population: a cadaveric study. J Cardiovasc Thorac Res 8(3):119

    Article  Google Scholar 

  36. Sonka M, Hlavac V, Boyle R (2014) Image processing, analysis, and machine vision. Cengage Learning

  37. De Vos BD, Wolterink JM, De Jong PA, Viergever MA, Išgum I (2016) 2D image classification for 3D anatomy localization: employing deep convolutional neural networks. In: Medical imaging 2016: image processing, vol 9784, International Society for Optics and Photonics, p 97841Y

  38. Freund Y, Schapire R, Abe N (1999) A short introduction to boosting. J Jpn Soc Artif Intell 14(771–780):1612

    Google Scholar 

  39. Zayed N, Elnemr HA (2015) Statistical analysis of haralick texture features to discriminate lung abnormalities. Int J Biomed Imaging

  40. Roffo G (2016) Feature selection library (MATLAB toolbox). arXiv:160701327

  41. Termeer M, Bescós JO, Breeuwer M, Vilanova A, Gerritsen F, Gröller E (2008) 1104 The volumetric bull’s eye plot. J Cardiovasc Magn Reson 10:1–3

    Article  Google Scholar 

  42. McCollough CH, Ulzheimer S, Halliburton SS, Shanneik K, White RD, Kalender WA (2007) Coronary artery calcium: a multi-institutional, multimanufacturer international standard for quantification at cardiac CT. Radiology 243(2):527–538

    Article  Google Scholar 

  43. Rumberger JA, Brundage BH, Rader DJ, Kondos G (1999) Electron beam computed tomographic coronary calcium scanning: a review and guidelines for use in asymptomatic persons. In: Mayo Clinic Proceedings, vol 74, Elsevier, pp 243–252

  44. Giavarina D (2015) Understanding Bland Altman analysis. Biochem Med 25(2):141–151

    Article  Google Scholar 

Download references

Acknowledgements

We acknowledge LASICOM laboratory and orCascore database. We express our sincere thanks to the General Directorate of Scientific Research and Technological Development (DGRSDT) for their support in the development of this work.

Funding

The authors received no specific funding for this work.

Author information

Authors and Affiliations

  1. LASICOM Laboratory, Department of Electronics, Faculty of Technology, University of Blida 1, 09000, Blida, Algeria

    Asmae Mama Zair, Assia Bouzouad Cherfa, Yazid Cherfa & Noureddine Belkhamsa

Authors
  1. Asmae Mama Zair
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Assia Bouzouad Cherfa
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yazid Cherfa
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Noureddine Belkhamsa
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

AMZ did the data collection. AMZ implemented the model and analyzed the data. AMZ wrote the manuscript with critical input from AC, YC, and NB. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Asmae Mama Zair.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zair, A.M., Bouzouad Cherfa, A., Cherfa, Y. et al. Machine learning for coronary artery calcification detection and labeling using only native computer tomography. Phys Eng Sci Med 45, 49–61 (2022). https://doi.org/10.1007/s13246-021-01080-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13246-021-01080-5

Keywords

Search

Navigation