Abstract
Coronary Artery Disease is developed when the blood vessels are narrowed, hindering the blood flow into the heart. An accurate assessment of stenosis and lesions is key for the success of Percutaneous Coronary Intervention, the standard procedure for the treatment of this pathology, which consists in the implantation of a stent in the narrowed part of the artery, allowing the correct blood flow. This is the aim of Quantitative Coronary Analysis (QCA), namely the measurement of the arteries diameter in the angiographies. Therefore, the automatic analysis of the QCA from angiograms is of interest for the clinical practice, supporting the decision making, risk assessment, and stent placement. This work proposes a set of tools required for the computation of the QCA, which include the application of deep learning and image processing techniques to angiograms for the automatic identification of contrast frames and the measurement of the diameter along the artery. The first stage of the work addresses the segmentation of the coronary tree, using a U-Net model trained with a self-built dataset, whose annotations have been semi-automatically obtained using edge-detection filters. This model is used for different applications, including the automatic identification of contrast frames, suitable for the QCA study, and the extraction of the vessels centerlines and the measurement of the diameter, useful for the analysis of possible lesions. Results of this process, obtained for a set of sequences captured from several patients are provided, demonstrating the validity of the methodology.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Abadi, M., et al.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems (2015). http://tensorflow.org/, software available from tensorflow.org
Bovik, A.C., Huang, T.S., Munson, D.C.: The effect of median filtering on edge estimation and detection. IEEE Trans. Patt. Anal. Mach. Intell. PAMI-9(2), 181–194 (1987). https://doi.org/10.1109/TPAMI.1987.4767894
Busto, L., et al.: Automatic identification of bioprostheses on X-ray angiographic sequences of transcatheter aortic valve implantation procedures using deep learning. Diagnostics 12(2) (2022). https://doi.org/10.3390/diagnostics12020334, https://www.mdpi.com/2075-4418/12/2/334
Cervantes-Sanchez, F., Cruz-Aceves, I., Hernandez-Aguirre, A., Hernandez-Gonzalez, M.A., Solorio-Meza, S.E.: Automatic segmentation of coronary arteries in x-ray angiograms using multiscale analysis and artificial neural networks. Appl. Sci. 9(24) (2019). https://www.mdpi.com/2076-3417/9/24/5507
Chollet, F., et al.: Keras. https://keras.io (2015)
Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Wells, W.M., Colchester, A., Delp, S. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 130–137. Springer, Heidelberg (1998). https://doi.org/10.1007/BFb0056195
Gupta, S., Gupta, A.: Dealing with noise problem in machine learning data-sets: a systematic review. Proc. Comput. Sci. 161, 466–474 (2019). https://doi.org/10.1016/j.procs.2019.11.146, https://www.sciencedirect.com/science/article/pii/S1877050919318575, the Fifth Information Systems International Conference, Surabaya, Indonesia, 23–24 July 2019
Kern, M., Samady, H.: Current concepts of integrated coronary physiology in the catheterization laboratory. J. Am. Coll. Cardiol. 55, 173–185 (2010)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). http://arxiv.org/abs/1412.6980, cite arxiv:1412.6980 Comment: Published as a conference paper at the 3rd International Conference for Learning Representations, San Diego (2015)
Mendis, S., Puska, P., Norrving, B.E., Organization, W.H., et al.: Global atlas on cardiovascular disease prevention and control. World Health Organization (2011)
Stone, P.H., et al.: Prediction of progression of coronary artery disease and clinical outcomes using vascular profiling of endothelial shear stress and arterial plaque characteristics. Prediction study. Circulation 126, 172–181 (2012). https://doi.org/10.1161/CIRCULATIONAHA.112.096438
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, May 2015
Sianos, G., et al.: The syntax score: an angiographic tool grading the complexity of coronary artery disease. EuroIntervention J. EuroPCR Collab. Working Group Intervent. Cardiol. Eur. Soc. Cardiol. 1(2), 219–227 (2005)
Stone, P.H.E.A.: Prediction of progression of coronary artery disease and clinical outcomes using vascular profiling of endothelial shear stress and arterial plaque characteristics: the prediction study. Circulation 126, 172–181 (2012)
Timmis, A., et al.: European society of cardiology: cardiovascular disease statistics 2019. Eur. Heart J. 41(1), 12–85 (2019). https://doi.org/10.1093/eurheartj/ehz859
Tonino, P.A., et al.: Fractional flow reserve versus angiography for guiding percutaneous coronary intervention. New England J. Med. 360(3), 213–224 (2009)
Topol, E.J., Teirstein, P.: Textbook of Interventional Cardiology, 8th Edition. Qualitative and Quantitative Coronary Angiography. Elsevier, ISBN: 9780323568142 (2019)
Tu, S., et al.: Fractional flow reserve calculation from 3-dimensional quantitative coronary angiography and TIMI frame count: a fast computer model to quantify the functional significance of moderately obstructed coronary arteries. JACC: Cardiovasc. Interv. 7(7), 768–777 (2014). https://doi.org/10.1016/j.jcin.2014.03.004, https://www.sciencedirect.com/science/article/pii/S1936879814007912
van der Walt, S., et al.: The scikit-image contributors: scikit-image: image processing in Python. PeerJ 2, e453 (2014). https://doi.org/10.7717/peerj.453
Yang, S., et al.: Deep learning segmentation of major vessels in X-ray coronary angiography. Sci. Rep. 9(1), 1–11 (2019)
Zhang, T.Y., Suen, C.Y.: A fast parallel algorithm for thinning digital patterns. Commun. ACM 27(3), 236–239 (1984)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Busto, L., González-Nóvoa, J.A., Juan-Salvadores, P., Jiménez, V., Íñiguez, A., Veiga, C. (2022). Using Deep Learning on X-ray Orthogonal Coronary Angiograms for Quantitative Coronary Analysis. In: Yang, G., Aviles-Rivero, A., Roberts, M., Schönlieb, CB. (eds) Medical Image Understanding and Analysis. MIUA 2022. Lecture Notes in Computer Science, vol 13413. Springer, Cham. https://doi.org/10.1007/978-3-031-12053-4_63
Download citation
DOI: https://doi.org/10.1007/978-3-031-12053-4_63
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12052-7
Online ISBN: 978-3-031-12053-4
eBook Packages: Computer ScienceComputer Science (R0)