Advertisement

European Radiology

, Volume 30, Issue 2, pp 1285–1294 | Cite as

Motion-corrected coronary calcium scores by a convolutional neural network: a robotic simulating study

  • Yaping Zhang
  • Niels R. van der Werf
  • Beibei Jiang
  • Robbert van Hamersvelt
  • Marcel J. W. Greuter
  • Xueqian XieEmail author
Imaging Informatics and Artificial Intelligence
  • 109 Downloads

Abstract

Objective

To classify motion-induced blurred images of calcified coronary plaques so as to correct coronary calcium scores on nontriggered chest CT, using a deep convolutional neural network (CNN) trained by images of motion artifacts.

Methods

Three artificial coronary arteries containing nine calcified plaques of different densities (high, medium, and low) and sizes (large, medium, and small) were attached to a moving robotic arm. The artificial arteries moving at 0–90 mm/s were scanned to generate nine categories (each from one calcified plaque) of images with motion artifacts. An inception v3 CNN was fine-tuned and validated. Agatston scores of the predicted classification by CNN were considered as corrected scores. Variation of Agatston scores on moving plaque and by CNN correction was calculated using the scores at rest as reference.

Results

The overall accuracy of CNN classification was 79.2 ± 6.1% for nine categories. The accuracy was 88.3 ± 4.9%, 75.9 ± 6.4%, and 73.5 ± 5.0% for the high-, medium-, and low-density plaques, respectively. Compared with the Agatston score at rest, the overall median score variation was 37.8% (1st and 3rd quartile, 10.5% and 68.8%) in moving plaques. CNN correction largely decreased the variation to 3.7% (1.9%, 9.1%) (p < 0.001, Mann–Whitney U test) and improved the sensitivity (percentage of non-zero scores among all the scores) from 65 to 85% for detection of coronary calcifications.

Conclusions

In this experimental study, CNN showed the ability to classify motion-induced blurred images and correct calcium scores derived from nontriggered chest CT. CNN correction largely reduces the overall Agatston score variation and increases the sensitivity to detect calcifications.

Key Points

• A deep CNN architecture trained by CT images of motion artifacts showed the ability to correct coronary calcium scores from blurred images.

• A correction algorithm based on deep CNN can be used for a tenfold reduction in Agatston score variations from 38 to 3.7% of moving coronary calcified plaques and to improve the sensitivity from 65 to 85% for the detection of calcifications.

• This experimental study provides a method to improve its accuracy for coronary calcium scores that is a fundamental step towards a real clinical scenario.

Keywords

Tomography, X-ray computed Phantoms, imaging Artifacts Artificial intelligence 

Abbreviations

CNN

Convolutional neural network

JPEG

Joint Photographic Experts Group

LAD

Left anterior descending artery

LCx

Left circumflex artery

NELSON

The Dutch-Belgian randomized lung cancer screening trial

RCA

Right coronary artery

Notes

Funding information

This study was sponsored by the National Natural Science Foundation of China (project no. 81471662), Ministry of Science and Technology of China (2016YFE0103000), Science and Technology Commission of Shanghai Municipality (16411968500 and 16410722300), Shanghai Municipal Education Commission – Gaofeng Clinical Medicine Grant Support (20181814), Shanghai Jiao Tong University (ZH2018ZDB10), and Clinical Research Innovation Plan of Shanghai General Hospital (CTCCR-2018B04). The funders played no role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Compliance with ethical standards

Guarantor

The scientific guarantor of this publication is Xueqian Xie, MD PhD, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

Xueqian Xie, MD PhD, performed deep learning.

Informed consent

Written informed consent was not required for this study because this is not a research on human subjects.

Ethical approval

Institutional Review Board approval was not required because this is not a research on human subjects.

Methodology

• Experimental

• Performed at one institution

Supplementary material

330_2019_6447_MOESM1_ESM.docx (233 kb)
ESM 1 (DOCX 232 kb)

References

  1. 1.
    Budoff MJ, Shaw LJ, Liu ST et al (2007) Long-term prognosis associated with coronary calcification: observations from a registry of 25,253 patients. J Am Coll Cardiol 49:1860–1870CrossRefGoogle Scholar
  2. 2.
    Berman DS, Arnson Y, Rozanski A (2016) Coronary artery calcium scanning: the Agatston score and beyond. JACC Cardiovasc Imaging 9:1417–1419CrossRefGoogle Scholar
  3. 3.
    Greenland P, Blaha MJ, Budoff MJ, Erbel R, Watson KE (2018) Coronary calcium score and cardiovascular risk. J Am Coll Cardiol 72:434–447CrossRefGoogle Scholar
  4. 4.
    Hecht HS, Blaha MJ, Kazerooni EA et al (2018) CAC-DRS: coronary artery calcium data and reporting system. An expert consensus document of the Society of Cardiovascular Computed Tomography (SCCT). J Cardiovasc Comput Tomogr 12:185–191CrossRefGoogle Scholar
  5. 5.
    Xie X, Greuter MJ, Groen JM et al (2013) Can nontriggered thoracic CT be used for coronary artery calcium scoring? A phantom study. Med Phys 40:081915CrossRefGoogle Scholar
  6. 6.
    Vonder M, Pelgrim GJ, Huijsse SEM et al (2017) Coronary artery calcium quantification on first, second and third generation dual source CT: a comparison study. J Cardiovasc Comput Tomogr 11:444–448CrossRefGoogle Scholar
  7. 7.
    Achenbach S, Ropers D, Holle J, Muschiol G, Daniel WG, Moshage W (2000) In-plane coronary arterial motion velocity: measurement with electron-beam CT. Radiology 216:457–463CrossRefGoogle Scholar
  8. 8.
    Husmann L, Leschka S, Desbiolles L et al (2007) Coronary artery motion and cardiac phases: dependency on heart rate - implications for CT image reconstruction. Radiology 245:567–576CrossRefGoogle Scholar
  9. 9.
    Xie X, Zhao Y, de Bock GH et al (2013) Validation and prognosis of coronary artery calcium scoring in nontriggered thoracic computed tomography: systematic review and meta-analysis. Circ Cardiovasc Imaging 6:514–521CrossRefGoogle Scholar
  10. 10.
    Mets OM, Vliegenthart R, Gondrie MJ et al (2013) Lung cancer screening CT-based prediction of cardiovascular events. JACC Cardiovasc Imaging 6:899–907CrossRefGoogle Scholar
  11. 11.
    Hecht H, Blaha MJ, Berman DS et al (2017) Clinical indications for coronary artery calcium scoring in asymptomatic patients: expert consensus statement from the Society of Cardiovascular Computed Tomography. J Cardiovasc Comput Tomogr 11:157–168CrossRefGoogle Scholar
  12. 12.
    van der Werf NR, Willemink MJ, Willems TP, Vliegenthart R, Greuter MJW, Leiner T (2018) Influence of heart rate on coronary calcium scores: a multi-manufacturer phantom study. Int J Cardiovasc Imaging 34:959–966CrossRefGoogle Scholar
  13. 13.
    Ma H, Gros E, Szabo A et al (2018) Evaluation of motion artifact metrics for coronary CT angiography. Med Phys 45:687–702CrossRefGoogle Scholar
  14. 14.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444CrossRefGoogle Scholar
  15. 15.
    He Y, Guo J, Ding X et al (2019) Convolutional neural network to predict the local recurrence of giant cell tumor of bone after curettage based on pre-surgery magnetic resonance images. Eur Radiol.  https://doi.org/10.1007/s00330-019-06082-2
  16. 16.
    Esteva A, Kuprel B, Novoa RA et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:115–118CrossRefGoogle Scholar
  17. 17.
    Zhao W, Yang J, Sun Y et al (2018) 3D deep learning from CT scans predicts tumor invasiveness of subcentimeter pulmonary adenocarcinomas. Cancer Res 78:6881–6889CrossRefGoogle Scholar
  18. 18.
    Sprem J, de Vos BD, Lessmann N, de Jong PA, Viergever MA, Isgum I (2018) Impact of automatically detected motion artifacts on coronary calcium scoring in chest computed tomography. J Med Imaging (Bellingham) 5:044007Google Scholar
  19. 19.
    Scott DS, Arora UK, Farb A, Virmani R, Weissman NJ (2000) Pathologic validation of a new method to quantify coronary calcific deposits in vivo using intravascular ultrasound. Am J Cardiol 85:37–40CrossRefGoogle Scholar
  20. 20.
    Moselewski F, Ferencik M, Achenbach S et al (2006) Threshold-dependent variability of coronary artery calcification measurements - implications for contrast-enhanced multi-detector row-computed tomography. Eur J Radiol 57:390–395CrossRefGoogle Scholar
  21. 21.
    Xie X, Zhao Y, Snijder R et al (2013) Sensitivity and accuracy of volumetry of pulmonary nodules on low-dose 16- and 64-row multi-detector CT: an anthropomorphic phantom study. Eur Radiol 23:139–147CrossRefGoogle Scholar
  22. 22.
    Blagus R, Lusa L (2015) Joint use of over- and under-sampling techniques and cross-validation for the development and assessment of prediction models. BMC Bioinformatics 16:363CrossRefGoogle Scholar
  23. 23.
    de Vos BD, Wolterink JM, Leiner T, de Jong PA, Lessmann N, Isgum I (2019) Direct automatic coronary calcium scoring in cardiac and chest CT. IEEE Trans Med Imaging.  https://doi.org/10.1109/TMI.2019.2899534
  24. 24.
    Xie Y, Liu S, Miller A et al (2017) Coronary artery calcification identification and labeling in low-dose chest CT images. Proc SPIE 10134, Medical Imaging: Computer-Aided Diagnosis, 101340LGoogle Scholar
  25. 25.
    Gonzalez G, Washko GR, Estepar RS (2016) Automated Agatston score computation in a large dataset of non-ECG-gated chest computed tomography. Proc IEEE Int Symp Biomed Imaging 2016:53–57PubMedPubMedCentralGoogle Scholar
  26. 26.
    Lessmann N, van Ginneken B, Zreik M et al (2018) Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions. IEEE Trans Med Imaging 37:615–625CrossRefGoogle Scholar
  27. 27.
    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 31:2322–2334CrossRefGoogle Scholar
  28. 28.
    Lossau T, Nickisch H, Wissel T et al (2019) Motion artifact recognition and quantification in coronary CT angiography using convolutional neural networks. Med Image Anal 52:68–79CrossRefGoogle Scholar
  29. 29.
    Elss T, Nickisch H, Wissel T, Bippus R, Morlock MM, Grass M (2018) Motion estimation in coronary CT angiography images using convolutional neural networks. 1st Conference on Medical Imaging with Deep Learning (MIDL 2018). Available via https://openreview.net/pdf?id=HkBtaBjoz. Accessed on 4 June 2019
  30. 30.
    Greuter MJ, Groen JM, Nicolai LJ, Dijkstra H, Oudkerk M (2009) A model for quantitative correction of coronary calcium scores on multidetector, dual source, and electron beam computed tomography for influences of linear motion, calcification density, and temporal resolution: a cardiac phantom study. Med Phys 36:5079–5088CrossRefGoogle Scholar
  31. 31.
    Contijoch F, Stayman JW, McVeigh ER (2017) The impact of small motion on the visualization of coronary vessels and lesions in cardiac CT: a simulation study. Med Phys 44:3512–3524CrossRefGoogle Scholar
  32. 32.
    Jacobs PC, Isgum I, Gondrie MJ et al (2010) Coronary artery calcification scoring in low-dose ungated CT screening for lung cancer: interscan agreement. AJR Am J Roentgenol 194:1244–1249CrossRefGoogle Scholar
  33. 33.
    Detrano R, Guerci AD, Carr JJ et al (2008) Coronary calcium as a predictor of coronary events in four racial or ethnic groups. N Engl J Med 358:1336–1345CrossRefGoogle Scholar
  34. 34.
    Blaha MJ, Cainzos-Achirica M, Greenland P et al (2016) Role of coronary artery calcium score of zero and other negative risk markers for cardiovascular disease: the multi-ethnic study of atherosclerosis (MESA). Circulation 133:849–858CrossRefGoogle Scholar
  35. 35.
    Jacobs PC, Gondrie MJ, van der Graaf Y et al (2012) Coronary artery calcium can predict all-cause mortality and cardiovascular events on low-dose CT screening for lung cancer. AJR Am J Roentgenol 198:505–511CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  1. 1.Radiology Department, Shanghai General HospitalShanghai Jiao Tong University School of MedicineShanghaiChina
  2. 2.Department of RadiologyUniversity Medical Center UtrechtUtrechtThe Netherlands
  3. 3.Department of Radiology & Nuclear MedicineErasmus University Medical CenterRotterdamThe Netherlands
  4. 4.University Medical Center Groningen, Radiology DepartmentUniversity of GroningenGroningenThe Netherlands

Personalised recommendations