Medical & Biological Engineering & Computing

, Volume 57, Issue 4, pp 863–876 | Cite as

Automated detection of vulnerable plaque in intravascular ultrasound images

  • Tae Joon JunEmail author
  • Soo-Jin Kang
  • June-Goo Lee
  • Jihoon Kweon
  • Wonjun Na
  • Daeyoun Kang
  • Dohyeun Kim
  • Daeyoung Kim
  • Young-Hak Kim
Original Article


Acute coronary syndrome (ACS) is a syndrome caused by a decrease in blood flow in the coronary arteries. The ACS is usually related to coronary thrombosis and is primarily caused by plaque rupture followed by plaque erosion and calcified nodule. Thin-cap fibroatheroma (TCFA) is known to be the most similar lesion morphologically to a plaque rupture. In this paper, we propose methods to classify TCFA using various machine learning classifiers including feed-forward neural network (FNN), K-nearest neighbor (KNN), random forest (RF), and convolutional neural network (CNN) to figure out a classifier that shows optimal TCFA classification accuracy. In addition, we suggest pixel range–based feature extraction method to extract the ratio of pixels in the different region of interests to reflect the physician’s TCFA discrimination criteria. Our feature extraction method examines the pixel distribution of the intravascular ultrasound (IVUS) image at a given ROI, which allows us to extract general characteristics of the IVUS image while simultaneously reflecting the different properties of the vessel’s substances such as necrotic core and calcified nodule depending on the brightness of the pixel. A total of 12,325 IVUS images were labeled with corresponding optical coherence tomography (OCT) images to train and evaluate the classifiers. We achieved 0.859, 0.848, 0.844, and 0.911 area under the ROC curve (AUC) in the order of using FNN, KNN, RF, and CNN classifiers. As a result, the CNN classifier performed best and the top 10 features of the feature-based classifiers (FNN, KNN, RF) were found to be similar to the physician’s TCFA diagnostic criteria.

Graphical Abstract

AUC result of proposed classifiers.


Vulnerable plaque Intravascular ultrasound Optical coherence tomography Machine learning Deep learning 



Support of Asan Medical Center providing IVUS images and clinical advices for this research is gratefully acknowledged.

Funding information

This research was supported by the International Research and Development Program of the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and Future Planning of Korea (2016K1A3A7A03952054).


  1. 1.
    Abadi M, Agarwal A, Barham P et al (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467
  2. 2.
    Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, OxfordGoogle Scholar
  3. 3.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32CrossRefGoogle Scholar
  4. 4.
    Calvert PA, Obaid DR, O’Sullivan M et al (2011) Association between IVUS findings and adverse outcomes in patients with coronary artery disease: the VIVA (VH-IVUS in Vulnerable Atherosclerosis) Study. JACC: Cardiovasc Imaging 4(8):894–901Google Scholar
  5. 5.
    Clevert DA, Unterthiner T, Hochreiter S (2015) Fast and accurate deep network learning by exponential linear units (elus). arXiv:1511.07289
  6. 6.
    Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121–2159Google Scholar
  7. 7.
    Fisher RA (1992) Statistical methods for research workers. In: Breakthroughs in Statistics. Springer, New York, pp 66–70Google Scholar
  8. 8.
    Garcia-Garcia HM, Costa MA, Serruys PW (2010) Imaging of coronary atherosclerosis: intravascular ultrasound. Eur Heart J 31(20):2456–2469CrossRefGoogle Scholar
  9. 9.
    Guyon I, Weston J, Barnhill S et al (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46(1-3):389–422CrossRefGoogle Scholar
  10. 10.
    He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770–778Google Scholar
  11. 11.
    Hosmer Jr DW, Lemeshow S, Sturdivant RX (2013) Applied logistic regression. Wiley, New YorkCrossRefGoogle Scholar
  12. 12.
    Inaba S, Mintz GS, Burke AP et al (2017) Intravascular ultrasound and near-infrared spectroscopic characterization of thin-cap fibroatheroma. Am J Cardiol 119(3):372–378CrossRefGoogle Scholar
  13. 13.
    Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167
  14. 14.
    Jang IK, Tearney GJ, MacNeill B, et al (2005) In vivo characterization of coronary atherosclerotic plaque by use of optical coherence tomography. Circulation 111(12):1551–1555CrossRefGoogle Scholar
  15. 15.
    Jun TJ, Kang SJ, Lee JG et al (2017) Thin-Cap fibroatheroma detection with deep neural networks. In: International Conference on Neural Information Processing, pp 759–768Google Scholar
  16. 16.
    Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980
  17. 17.
    Kolodgie FD, Burke AP, Farb A et al (2001) The thin-cap fibroatheroma: a type of vulnerable plaque: the major precursor lesion to acute coronary syndromes. Curr Opin Cardiol 16(5):285–292CrossRefGoogle Scholar
  18. 18.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105Google Scholar
  19. 19.
    LeCun Y, Boser B, Denker JS et al (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541–551CrossRefGoogle Scholar
  20. 20.
    Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. Int Conf Mach Learn 30(1):3Google Scholar
  21. 21.
    McDonald JH (2009) Handbook of biological statistics. Sparky House Publishing, Baltimore, pp 173–181Google Scholar
  22. 22.
    Nissen SE, Yock P (2001) Intravascular ultrasound: novel pathophysiological insights and current clinical applications. Circulation 103(4):604–616CrossRefGoogle Scholar
  23. 23.
    Pedregosa F, Varoquaux G, Gramfort A (2011) Scikit-learn: m learning in Python. J Mach Learn Res 12:2825–2830Google Scholar
  24. 24.
    Plackett RL (1983) Karl Pearson and the chi-squared test. Int Stat Rev/Revue Internationale de Statistique 51(1):59–72Google Scholar
  25. 25.
    Rodriguez-Granillo GA, García-García HM, Mc Fadden EP et al (2005) In vivo intravascular ultrasound-derived thin-cap fibroatheroma detection using ultrasound radiofrequency data analysis. J Am Coll Cardiol 46(11):2038–2042CrossRefGoogle Scholar
  26. 26.
    Russakovsky O, Deng J, Su H et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211– 252CrossRefGoogle Scholar
  27. 27.
    Sawada T, Shite J, Garcia-Garcia HM et al (2008) Feasibility of combined use of intravascular ultrasound radiofrequency data analysis and optical coherence tomography for detecting thin-cap fibroatheroma. Eur Heart J 29(9):1136–1146CrossRefGoogle Scholar
  28. 28.
    Simard PY, Steinkraus D, Platt JC (2003) Best practices for convolutional neural networks applied to visual document analysis. In: International Conference on Document Analysis and Recognition, pp 958–962Google Scholar
  29. 29.
    Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
  30. 30.
    Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958Google Scholar
  31. 31.
    Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition, pp 1–9Google Scholar
  32. 32.
    Tieleman T, Hinton G (2012) Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: neural networks for machine learning 4(2):26–31Google Scholar
  33. 33.
    Virmani R, Burke AP, Farb A et al (2006) Pathology of the vulnerable plaque. J Am Coll Cardiol 47.8 (Supplement):13–18CrossRefGoogle Scholar
  34. 34.
    Wolf I, Vetter M, Wegner I et al (2005) The medical imaging interaction toolkit. Med Image Anal 9(6):594–604CrossRefGoogle Scholar
  35. 35.
    Zeiler MD (2012) ADADELTA: an adaptive learning rate method. arXiv:1212.5701
  36. 36.
    Zeiler MD, Fergus R (2013) Stochastic pooling for regularization of deep convolutional neural networks. arXiv:1301.3557
  37. 37.
    Zhang L, Wahle A, Chen Z et al (2015) Prospective prediction of thin-cap fibroatheromas from baseline virtual histology intravascular ultrasound data. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp 603–610Google Scholar
  38. 38.
    Zhou B, Khosla A, Lapedriza A et al (2016) Learning deep features for discriminative localization. In: IEEE conference on computer vision and pattern recognition, pp 2921–2929Google Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2018

Authors and Affiliations

  1. 1.School of ComputingKorea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea
  2. 2.Division of CardiologyUniversity of Ulsan College of Medicine, Asan Medical CenterSeoulRepublic of Korea
  3. 3.Asan Institute for Life SciencesAsan Medical CenterSeoulRepublic of Korea

Personalised recommendations