Abstract
Coronary Artery Calcium Score (CACS) is a prognostic indicator for coronary atherosclerosis that can cause a stroke or heart attack. Cardiac computed tomography (CT) is widely used to calculate CACS. For asymptomatic patients, however, a CT-based screening tes is not recommended due to an unnecessary exposure to radiation and high cost. In this paper, we propose a deep learning approach to predict CACS from retinal fundus photographs. Our approach is non-invasive and can observe blood vessels without any side effects. Contrasted to other approaches, we can predict CACS directly using only retinal fundus photographs without the electronic health record (EHR) data. To overcome data deficiency, we train deep convolutional neural nets (CNNs) with retinal fundus images for predicting auxiliary EHR data related to CACS. In addition, we employ a task-specific augmentation method that resolves flare phenomenon typically occurred in a retinal fundus image. Our empirical results indicate that the use of auxiliary EHR data improves the CACS prediction performance by 4.2%, and flare augmentation by 2.4% on area under the ROC curve (AUC). Applying both methods results in an overall 6.2% improvement. In the light of feature extraction and inference uncertainty, our deep learning models can predict CACS using only retinal fundus images and identify individuals with a cardiovascular disease.
S. Cho–First author
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
References
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)
Alluri, K., Joshi, P.H., Henry, T.S., Blumenthal, R.S., Nasir, K., Blaha, M.J.: Scoring of coronary artery calcium scans: history, assumptions, current limitations, and future directions. Atherosclerosis 239(1), 109–117 (2015)
Blaha, M.J.: Personalizing treatment: between primary and secondary prevention. Am. J. Cardiol. 118(6), 4A–12A (2016)
Brahim, A.B., Limam, M.: Ensemble feature selection for high dimensional data: a new method and a comparative study. Adv. Data Anal. Classif. 12(4), 937–952 (2018)
Budoff, M.J., et al.: Assessment of coronary artery disease by cardiac computed tomography: a scientific statement from the american heart association committee on cardiovascular imaging and intervention, council on cardiovascular radiology and intervention, and committee on cardiac imaging, council on clinical cardiology. Circulation 114(16), 1761–1791 (2006)
Burlina, P.M., Joshi, N., Pekala, M., Pacheco, K.D., Freund, D.E., Bressler, N.M.: Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophthalmol. 135(11), 1170–1176 (2017)
Curry, S.J., et al.: Risk assessment for cardiovascular disease with nontraditional risk factors: us preventive services task force recommendation statement. JAMA 320(3), 272–280 (2018)
Gal, Y.: Uncertainty in deep learning. Ph.D. thesis, University of Cambridge (2016)
Greenland, P., Blaha, M.J., Budoff, M.J., Erbel, R., Watson, K.E.: Coronary calcium score and cardiovascular risk. J. Am. Coll. Cardiol. 72(4), 434–447 (2018)
Gulshan, V., et al.: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316(22), 2402–2410 (2016)
Jellinger, P.S., et al.: American association of clinical endocrinologists and American college of endocrinology guidelines for management of dyslipidemia and prevention of cardiovascular disease. Endocr. Pract. 23(s2), 1–87 (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Lessmann, N., et al.: Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions. IEEE Trans. Med. Imaging 37(2), 615–625 (2017)
Li, Z., He, Y., Keel, S., Meng, W., Chang, R.T., He, M.: Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology 125(8), 1199–1206 (2018)
McClintic, B.R., McClintic, J.I., Bisognano, J.D., Block, R.C.: The relationship between retinal microvascular abnormalities and coronary heart disease: a review. Am. J. Med. 123(4), 374 e1–374 e7 (2010)
Poplin, R., et al.: Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nature Biomed. Eng. 2(3), 158 (2018)
Saeys, Y., Abeel, T., Van de Peer, Y.: Robust feature selection using ensemble feature selection techniques. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008. LNCS (LNAI), vol. 5212, pp. 313–325. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-87481-2_21
Santini, G., et al.: An automatic deep learning approach for coronary artery calcium segmentation. EMBEC/NBC -2017. IP, vol. 65, pp. 374–377. Springer, Singapore (2018). https://doi.org/10.1007/978-981-10-5122-7_94
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Tabatabaee, A., Asharin, M., Dehghan, M., Pourbehi, M., Nasiri-Ahmadabadi, M., Assadi, M.: Retinal vessel abnormalities predict coronary artery diseases. Perfusion 28(3), 232–237 (2013)
Wang, J.J., et al.: Retinal vessel diameter and cardiovascular mortality: pooled data analysis from two older populations. Eur. Heart J. 28(16), 1984–1992 (2007)
Wong, T.Y., et al.: Relation of retinopathy to coronary artery calcification: the multi-ethnic study of atherosclerosis. Am. J. Epidemiol. 167(1), 51–58 (2007)
World Health Organisation: Fact sheet cardiovascular diseases (CVDS) (2017)
Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048–2057 (2015)
Acknowledgement
We thank Youngjune Gwon (Vice President, Samsung SDS) for improving the manuscript.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Cho, S. et al. (2020). Predicting Coronary Artery Calcium Score from Retinal Fundus Photographs Using Convolutional Neural Networks. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2020. Lecture Notes in Computer Science(), vol 12415. Springer, Cham. https://doi.org/10.1007/978-3-030-61401-0_56
Download citation
DOI: https://doi.org/10.1007/978-3-030-61401-0_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61400-3
Online ISBN: 978-3-030-61401-0
eBook Packages: Computer ScienceComputer Science (R0)