Automatic Detection of Non-Biological Artifacts in ECGs Acquired During Cardiac Computed Tomography

  • Rustem Bekmukhametov
  • Sebastian Pölsterl
  • Thomas Allmendinger
  • Minh-Duc Doan
  • Nassir Navab
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9853)


Cardiac computed tomography is a non-invasive technique to image the beating heart. One of the main concerns during the procedure is the total radiation dose imposed on the patient. Prospective electrocardiographic (ECG) gating methods may notably reduce the radiation exposure. However, very few investigations address accompanying problems encountered in practice. Several types of unique non-biological factors, such as the dynamic electrical field induced by rotating components in the scanner, influence the ECG and can result in artifacts that can ultimately cause prospective ECG gating algorithms to fail. In this paper, we present an approach to automatically detect non-biological artifacts within ECG signals, acquired in this context. Our solution adapts discord discovery, robust PCA, and signal processing methods for detecting such disturbances. It achieved an average area under the precision-recall curve (AUPRC) and receiver operating characteristics curve (AUROC) of 0.996 and 0.997 in our cross-validation experiments based on 2,581 ECGs. External validation on a separate hold-out dataset of 150 ECGs, annotated by two domain experts (88 % inter-expert agreement), yielded average AUPRC and AUROC scores of 0.890 and 0.920. Our solution is deployed to automatically detect non-biological anomalies within a continuously updated database, currently holding over 120,000 ECGs.


Anomaly detection Cardiac computed tomography Electrocardiography Prospective ECG gating 



This work was supported by Siemens Healthcare GmbH.


  1. 1.
    Biel, L., Pettersson, O., Philipson, L., Wide, P.: ECG analysis: a new approach in human identification. IEEE Trans. Instrum. Meas. 50(3), 808–812 (2001)CrossRefGoogle Scholar
  2. 2.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Candes, E.J., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM 58(3) (2011). Article Number 11Google Scholar
  4. 4.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar
  5. 5.
    De Chazal, P., Dwyer, M.O., Reilly, R.B.: Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Trans. Biomed. Eng. 51(7), 1196–1206 (2004)CrossRefGoogle Scholar
  6. 6.
    Donoho, D.L.: De-noising by soft-thresholding. IEEE Trans. Inf. Theor. 41(3), 613–627 (1995)MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Esarey, J., Pierce, A.: Assessing fit quality and testing for misspecification in binary-dependent variable models. Polit. Anal. 20(4), 480–500 (2012)CrossRefGoogle Scholar
  8. 8.
    Fix, E., Hodges, J.L.: Discriminatory analysis - nonparametric discrimination: consistency properties. Technical report, USAF School of Aviation Medicine, Randolph Field, TX (1951)Google Scholar
  9. 9.
    Hausleiter, J., Meyer, T.S., Martuscelli, E., Spagnolo, P., Yamamoto, H., Carrascosa, P., Anger, T., Lehmkuhl, L., Alkadhi, H., Martinoff, S., et al.: Image quality and radiation exposure with prospectively ECG-triggered axial scanning for coronary CT angiography: the multicenter, multivendor, randomized PROTECTION-III study. JACC Cardiovasc. Imaging 5(5), 484–493 (2012)CrossRefGoogle Scholar
  10. 10.
    Hsieh, J., Londt, J., Vass, M., Li, J., Tang, X., Okerlund, D.: Step-and-shoot data acquisition and reconstruction for cardiac x-ray computed tomography. Med. Phys. 33(11), 4236–4248 (2006)CrossRefGoogle Scholar
  11. 11.
    Karpagachelvi, S., Arthanari, M., Sivakumar, M.: ECG feature extraction techniques - a survey approach. Int. J. Comput. Sci. Inf. Secur. 8(1), 76–80 (2010)Google Scholar
  12. 12.
    Kendall, M.G., Smith, B.B.: The problem of \(m\) rankings. Ann. Math. Stat. 10(3), 275–287 (1939)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Keogh, E., Lin, J., Fum, A.: Hot SAX: Efficiently finding the most unusual time series subsequence. In: 5th IEEE International Conference Data Mining, pp. 226–233. IEEE Computer Society, Washington, DC (2005)Google Scholar
  14. 14.
    Lin, J., Keogh, E., Wei, L., Lonardi, S.: Experiencing SAX: a novel symbolic representation of time series. Data Min. Knowl. Discov. 15(2), 107–144 (2007)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Mallat, S.G.: A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. 11(7), 674–693 (1989)CrossRefzbMATHGoogle Scholar
  16. 16.
    Rosner, B.: Percentage points for a generalized ESD many-outlier procedure. Technometrics 25(2), 165–172 (1983)CrossRefzbMATHGoogle Scholar
  17. 17.
    Vintsyuk, T.K.: Speech discrimination by dynamic programming. Cybern Syst. Anal. 4(1), 52–57 (1968)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Widrow, B., Glover, J.R., McCool, J.M., Kaunitz, J., Williams, C.S., Hearn, R.H., Zeidler, J.R., Dong, E., Goodlin, R.C.: Adaptive noise cancelling: Principles and applications. Proc. IEEE 63(12), 1692–1716 (1975)CrossRefGoogle Scholar
  19. 19.
    Wolpert, D.: Stacked generalization. Neural Netw. 5(2), 241–260 (1992)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Rustem Bekmukhametov
    • 1
  • Sebastian Pölsterl
    • 1
  • Thomas Allmendinger
    • 2
  • Minh-Duc Doan
    • 2
  • Nassir Navab
    • 1
    • 3
  1. 1.Computer Aided Medical ProceduresTechnische Universität MünchenMunichGermany
  2. 2.Diagnostic Imaging and Computed TomographySiemens Healthcare GmbHForchheimGermany
  3. 3.Johns Hopkins UniversityBaltimoreUSA

Personalised recommendations