On the Relevance of the Loss Function in the Agatston Score Regression from Non-ECG Gated CT Scans

  • Carlos Cano-EspinosaEmail author
  • Germán González
  • George R. Washko
  • Miguel Cazorla
  • Raúl San José Estépar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11040)


In this work, we evaluate the relevance of the choice of loss function in the regression of the Agatston score from 3D heart volumes obtained from non-contrast non-ECG gated chest computed tomography scans. The Agatston score is a well-established metric of cardiovascular disease, where an index of coronary artery disease (CAD) is computed by segmenting the calcifications of the arteries and multiplying each calcification by a factor related to their intensity and their volume, creating a final aggregated index. Recent work has automated such task with deep learning techniques, even skipping the segmentation step and performing a direct regression of the Agatston score. We study the effect of the choice of the loss function in such methodologies. We use a large database of 6983 CT scans to which the Agatston score has been manually computed. The dataset is split into a training set and a validation set of \(n=1000\). We train a deep learning regression network using such data with different loss functions while keeping the structure of the network and training parameters constant. Pearson correlation coefficient ranges from 0.902 to 0.938 depending on the loss function. Correct risk group assignment measurements range between \(59.5\%\) and \(81.7\%\). There is a trade-off between the accuracy of the Pearson correlation coefficient and the risk group measurement, which leads to optimize for one or the other.


Loss functions Agatston score Regression Convolutional 


  1. 1.
    Agatston, A.S., Janowitz, W.R., Hildner, F.J., Zusmer, N.R., Viamonte, M., Detrano, R.: Quantification of coronary artery calcium using ultrafast computed tomography. J. Am. Coll. Cardiol. 15(4), 827–832 (1990)CrossRefGoogle Scholar
  2. 2.
    Cano-Espinosa, C., Gonzlez, G., Washko, G.R., Cazorla, M., Estépar, R.S.J.: Automated Agatston score computation in non-ECG gated CT scans using deep learning. In: Proceedings of the SPIE: Medical Imaging 2018, February 2018Google Scholar
  3. 3.
    Erbel, R., Möhlenkamp, S., Kerkhoff, G., Budde, T., Schmermund, A.: Non-invasive screening for coronary artery disease: calcium scoring. Heart 93(12), 1620–1629 (2007)CrossRefGoogle Scholar
  4. 4.
    González, G., Washko, G.R., Estépar, R.S.J.: Automated Agatston score computation in a large dataset of non ECG-gated chest computed tomography. In: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), pp. 53–57. IEEE (2016)Google Scholar
  5. 5.
    Gonzlez, G., Washko, G.R., Estépar, R.S.J.: Deep learning for biomarker regression. Application to osteoporosis and emphysema on chest CT scans. In: Proceedings of the SPIE: Medical Imaging 2018, February 2018Google Scholar
  6. 6.
    Isgum, I., Prokop, M., Niemeijer, M., Viergever, M.A., van Ginneken, B.: Automatic coronary calcium scoring in low-dose chest computed tomography. IEEE Trans. Med. Imaging 31(12), 2322–2334 (2012)CrossRefGoogle Scholar
  7. 7.
    Isgum, I., Staring, M., Rutten, A., Prokop, M., Viergever, M.A., Van Ginneken, B.: Multi-atlas-based segmentation with local decision fusion—application to cardiac and aortic segmentation in CT scans. IEEE Trans. Med. Imaging 28(7), 1000–1010 (2009)CrossRefGoogle Scholar
  8. 8.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  9. 9.
    Reeves, A.P., Biancardi, A.M., Yankelevitz, D.F., Cham, M.D., Henschke, C.I.: Heart region segmentation from low-dose CT scans: an anatomy based approach. In: Medical Imaging: Image Processing, p. 83142A (2012)Google Scholar
  10. 10.
    Regan, E.A., et al.: Genetic epidemiology of COPD (COPDgene) study design. COPD J. Chronic Obstr. Pulm. Dis. 7(1), 32–43 (2011)CrossRefGoogle Scholar
  11. 11.
    Rodriguez-Lopez, S., et al.: Automatic ventricle detection in computed tomography pulmonary angiography. In: 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), pp. 1143–1146. IEEE (2015)Google Scholar
  12. 12.
    Shahzad, R., et al.: Vessel specific coronary artery calcium scoring: an automatic system. Acad. Radiol. 20(1), 1–9 (2013)CrossRefGoogle Scholar
  13. 13.
    Wolterink, J.M., Leiner, T., Takx, R.A., Viergever, M.A., Išgum, I.: 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, p. 90350E. International Society for Optics and Photonics (2014)Google Scholar
  14. 14.
    Wolterink, J.M., Leiner, T., Viergever, M.A., Išgum, I.: Automatic coronary calcium scoring in cardiac CT angiography using convolutional neural networks. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 589–596. Springer, Cham (2015). Scholar
  15. 15.
    Wolterink, J.M., Leiner, T., de Vos, B.D., van Hamersvelt, R.W., Viergever, M.A., Išgum, I.: Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks. Med. Image Anal. 34, 123–136 (2016)CrossRefGoogle Scholar
  16. 16.
    Xie, Y., Cham, M.D., Henschke, C., Yankelevitz, D., Reeves, A.P.: Automated coronary artery calcification detection on low-dose chest CT images. In: Proceedings of SPIE, vol. 9035, p. 90350F (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of Computer Science and Artificial IntelligenceUniversity of AlicanteAlicanteSpain
  2. 2.Sierra Research SLAlicanteSpain
  3. 3.Brigham and Women’s Hospital, Pulmonary and Critical Care MedicineBostonUSA
  4. 4.Applied Chest Imaging Laboratory, Department of RadiologyBrigham and Women’s Hospital, Harvard Medical SchoolBostonUSA

Personalised recommendations