Abstract
Cardiovascular disease (CVD) stands as the leading global cause of mortality, and coronary artery disease (CAD) has the highest prevalence, contributing to 42% of these fatalities. Recognizing the constraints inherent in the anatomical assessment of CAD, Fractional Flow Reserve (FFR) has emerged as a pivotal functional diagnostic metric. Herein, we assess the potential of employing an ensemble approach with deep neural networks (DNN) to predict invasively measured Fractional Flow Reserve (FFR) using raw anatomical data extracted from both optical coherence tomography (OCT) and X-ray coronary angiography (XA). In this study, we used a challenging dataset, with 46% of the lesions falling within the FFR range of 0.75 to 0.85. Despite this complexity, our model achieved an accuracy of 84.3%, demonstrating a sensitivity of 87.5% and a specificity of 81.4%. Our results demonstrate that incorporating both OCT and XA signals, co-registered, as inputs for the DNN model leads to an important increase in overall accuracy.
Similar content being viewed by others
References
Roth GA, Johnson C, Abajobir A, Abd-Allah F, Abera SF, Abyu G et al (2017) Global, regional, and national burden of cardiovascular diseases for 10 causes, 1990 to 2015. J Am Coll Cardiol 70(1):1–25
Ryan TJ (2002) The coronary angiogram and its seminal contributions to cardiovascular medicine over five decades. Circulation 106(6):752–756
Gutierrez-Chico JL, Alegría-Barrero E, Teijeiro-Mestre R, Chan PH, Tsujioka H, de Silva R et al (2012) Optical coherence tomography: from research to practice. Eur Heart Journal–Cardiovascular Imaging 13(5):370–384
Gutiérrez-Chico JL, Regar E, Nüesch E, Okamura T, Wykrzykowska J, di Mario C et al (2011) Delayed coverage in malapposed and side-branch struts with respect to well-apposed struts in drug-eluting stents: in vivo assessment with optical coherence tomography. Circulation 124(5):612–623
Gutiérrez-Chico JL, Wykrzykowska J, Nüesch E, van Geuns RJ, Koch KT, Koolen JJ et al (2012) Vascular tissue reaction to acute malapposition in human coronary arteries: sequential assessment with optical coherence tomography. Circulation: Cardiovasc Interventions 5(1):20–29
Ali ZA, Maehara A, Généreux P, Shlofmitz RA, Fabbiocchi F, Nazif TM et al (2016) Optical coherence tomography compared with intravascular ultrasound and with angiography to guide coronary stent implantation (ILUMIEN III: OPTIMIZE PCI): a randomised controlled trial. Lancet 388(10060):2618–2628
Gonzalo N, Escaned J, Alfonso F, Nolte C, Rodriguez V, Jimenez-Quevedo P et al (2012) Morphometric assessment of coronary stenosis relevance with optical coherence tomography: a comparison with fractional flow reserve and intravascular ultrasound. J Am Coll Cardiol 59(12):1080–1089
Pijls NH, de Bruyne B, Peels K, van der Voort PH, Bonnier HJ, Bartunek J et al (1996) Measurement of fractional flow reserve to assess the functional severity of coronary-artery stenoses. N Engl J Med 334(26):1703–1708
Tonino PA, De Bruyne B, Pijls NH, Siebert U, Ikeno F, vant Veer M et al (2009) Fractional flow reserve versus angiography for guiding percutaneous coronary intervention. N Engl J Med 360(3):213–224
Tu S, Bourantas CV, Nørgaard BL, Kassab GS, Koo BK, Reiber J (2015) Image-based assessment of fractional flow reserve. EuroIntervention: journal of EuroPCR in collaboration with the Working Group on Interventional Cardiology of the European Society of Cardiology. 11:V50–V54
Yang DH, Kim Y-H, Roh JH, Kang J-W, Ahn J-M, Kweon J et al (2017) Diagnostic performance of on-site CT-derived fractional flow reserve versus CT perfusion. Eur Heart Journal–Cardiovascular Imaging 18(4):432–440
Coenen A, Lubbers MM, Kurata A, Kono A, Dedic A, Chelu RG et al (2015) Fractional flow reserve computed from noninvasive CT angiography data: diagnostic performance of an on-site clinician-operated computational fluid dynamics algorithm. Radiology 274(3):674–683
Renker M, Schoepf UJ, Wang R, Meinel FG, Rier JD, Bayer IIRR et al (2014) Comparison of diagnostic value of a novel noninvasive coronary computed tomography angiography method versus standard coronary angiography for assessing fractional flow reserve. Am J Cardiol 114(9):1303–1308
Koo B-K, Erglis A, Doh J-H, Daniels DV, Jegere S, Kim H-S et al (2011) Diagnosis of ischemia-causing coronary stenoses by noninvasive fractional flow reserve computed from coronary computed tomographic angiograms: results from the prospective multicenter DISCOVER-FLOW (diagnosis of ischemia-causing Stenoses Obtained Via Noninvasive Fractional Flow Reserve) study. J Am Coll Cardiol 58(19):1989–1997
Tu S, Westra J, Yang J, von Birgelen C, Ferrara A, Pellicano M et al (2016) Diagnostic accuracy of fast computational approaches to derive fractional flow reserve from diagnostic coronary angiography: the international multicenter FAVOR pilot study. Cardiovasc Interventions 9(19):2024–2035
Tröbs M, Achenbach S, Röther J, Redel T, Scheuering M, Winneberger D et al (2016) Comparison of fractional flow reserve based on computational fluid dynamics modeling using coronary angiographic vessel morphology versus invasively measured fractional flow reserve. Am J Cardiol 117(1):29–35
Papafaklis MI, Muramatsu T, Ishibashi Y, Lakkas LS, Nakatani S, Bourantas CV et al (2014) Fast virtual functional assessment of intermediate coronary lesions using routine angiographic data and blood flow simulation in humans: comparison with pressure wire-fractional flow reserve. EuroIntervention: J EuroPCR Collab Working Group Interventional Cardiol Eur Soc Cardiol 10(5):574–583
Tu S, Barbato E, Köszegi Z, Yang J, Sun Z, Holm NR et al (2014) 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 Interventions 7(7):768–777
Morris PD, Ryan D, Morton AC, Lycett R, Lawford PV, Hose DR et al (2013) Virtual fractional flow reserve from coronary angiography: modeling the significance of coronary lesions: results from the VIRTU-1 (VIRTUal fractional Flow Reserve from Coronary Angiography) study. JACC: Cardiovasc Interventions 6(2):149–157
Seike F, Uetani T, Nishimura K, Kawakami H, Higashi H, Aono J et al (2017) Intracoronary optical coherence tomography-derived virtual fractional flow reserve for the assessment of coronary artery disease. Am J Cardiol 120(10):1772–1779
Jang S-J, Ahn J-M, Kim B, Gu J-M, Sung HJ, Park S-J et al (2017) Comparison of accuracy of one-use methods for calculating fractional flow reserve by intravascular optical coherence tomography to that determined by the pressure-wire method. Am J Cardiol 120(11):1920–1925
Yu W, Huang J, Jia D, Chen S, Raffel OC, Ding D et al (2019) Diagnostic accuracy of intracoronary optical coherence tomography-derived fractional flow reserve for assessment of coronary stenosis severity. EuroIntervention: J EuroPCR Collab Working Group Interventional Cardiol Eur Soc Cardiol 15(2):189
Ha J, Kim J-S, Lim J, Kim G, Lee S, Lee JS et al (2016) Assessing computational fractional flow reserve from optical coherence tomography in patients with intermediate coronary stenosis in the left anterior descending artery. Circulation: Cardiovasc Interventions 9(8):e003613
Itu L, Sharma P, Mihalef V, Kamen A, Suciu C, Lomaniciu D (2012) A patient-specific reduced-order model for coronary circulation. 2012 9th IEEE international symposium on biomedical imaging (ISBI): IEEE; p. 832-5
Deng S-B, **g X-D, Wang J, Huang C, **a S, Du J-L et al (2015) Diagnostic performance of noninvasive fractional flow reserve derived from coronary computed tomography angiography in coronary artery disease: a systematic review and meta-analysis. Int J Cardiol 184:703–709
Bishop CM, Nasrabadi NM (2006) Pattern recognition and machine learning, vol 4. Springer
Zheng Y, Comaniciu D (2014) Marginal space learning for medical image analysis. Springer
Mansi T, Georgescu B, Hussan J, Hunter PJ, Kamen A, Comaniciu D (2013) Data-driven reduction of a cardiac myofilament model. Functional Imaging and Modeling of the Heart: 7th International Conference, FIMH 2013, London, UK, June 20–22, 2013 Proceedings 7: Springer; p. 232 – 40
Tøndel K, Indahl UG, Gjuvsland AB, Vik JO, Hunter P, Omholt SW et al (2011) Hierarchical cluster-based partial least squares Regression (HC-PLSR) is an efficient tool for metamodelling of nonlinear dynamic models. BMC Syst Biol 5(1):1–17
Itu L, Rapaka S, Passerini T, Georgescu B, Schwemmer C, Schoebinger M et al (2016) A machine-learning approach for computation of fractional flow reserve from coronary computed tomography. J Appl Physiol 121(1):42–52
Cho H, Lee JG, Kang SJ, Kim WJ, Choi SY, Ko J et al (2019) Angiography-based machine learning for predicting fractional flow reserve in intermediate coronary artery lesions. J Am Heart Association 8(4):e011685
Cha J-J, Son TD, Ha J, Kim J-S, Hong S-J, Ahn C-M et al (2020) Optical coherence tomography-based machine learning for predicting fractional flow reserve in intermediate coronary stenosis: a feasibility study. Sci Rep 10(1):20421
Lee J-G, Ko J, Hae H, Kang S-J, Kang D-Y, Lee PH et al (2020) Intravascular ultrasound-based machine learning for predicting fractional flow reserve in intermediate coronary artery lesions. Atherosclerosis 292:171–177
Deng L, Yu D (2014) Deep learning: methods and applications. Found trends® Signal Process 7(3–4):197–387
Wang Y, Yao Q, Kwok JT, Ni LM (2020) Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv (csur) 53(3):1–34
Jiang X, Zeng Y, **ao S, He S, Ye C, Qi Y et al (2020) Automatic detection of coronary metallic stent struts based on YOLOv3 and R-FCN. Computational and mathematical methods in medicine. ;2020
Wang Z, Jenkins MW, Linderman GC, Bezerra HG, Fu**o Y, Costa MA et al (2015) 3-D stent detection in intravascular OCT using a bayesian network and graph search. IEEE Trans Med Imaging 34(7):1549–1561
Wu P, Gutiérrez-Chico JL, Tauzin H, Yang W, Li Y, Yu W et al (2020) Automatic stent reconstruction in optical coherence tomography based on a deep convolutional model. Biomedical Opt Express 11(6):3374–3394
Yang G, Mehanna E, Li C, Zhu H, He C, Lu F et al (2021) Stent detection with very thick tissue coverage in intravascular OCT. Biomedical Opt Express 12(12):7500–7516
Lau YS, Tan LK, Chan CK, Chee KH, Liew YM (2021) Automated segmentation of metal stent and bioresorbable vascular scaffold in intravascular optical coherence tomography images using deep learning architectures. Phys Med Biol 66(24):245026
Lee J, Gharaibeh Y, Kolluru C, Zimin VN, Dallan LAP, Kim JN et al (2020) Segmentation of coronary calcified plaque in intravascular OCT images using a two-step deep learning approach. IEEE Access 8:225581–225593
Gharaibeh Y, Prabhu D, Kolluru C, Lee J, Zimin V, Bezerra H et al (2019) Coronary calcification segmentation in intravascular OCT images using deep learning: application to calcification scoring. J Med Imaging 6(4):045002
Abdolmanafi A, Duong L, Ibrahim R, Dahdah N (2021) A deep learning-based model for characterization of atherosclerotic plaque in coronary arteries using optical coherence tomography images. Med Phys 48(7):3511–3524
Pociask E, Malinowski KP, Ślęzak M, Jaworek-Korjakowska J, Wojakowski W, Roleder T (2018) Fully automated lumen segmentation method for intracoronary optical coherence tomography. Journal of Healthcare Engineering. ;2018
Jiao C, Xu Z, Bian Q, Forsberg E, Tan Q, Peng X et al (2021) Machine learning classification of origins and varieties of Tetrastigma hemsleyanum using a dual-mode microscopic hyperspectral imager. Spectrochim Acta Part A Mol Biomol Spectrosc 261:120054
Wang T, Shen F, Deng H, Cai F, Chen S (2022) Smartphone imaging spectrometer for egg/meat freshness monitoring. Anal Methods 14(5):508–517
Kern MJ, Lerman A, Bech J-W, De Bruyne B, Eeckhout E, Fearon WF et al (2006) Physiological assessment of coronary artery disease in the cardiac catheterization laboratory: a scientific statement from the American Heart Association Committee on Diagnostic and Interventional Cardiac Catheterization, Council on Clinical Cardiology. Circulation 114(12):1321–1341
Optical Coherence Tomography (OCT) Intravascular Imaging | Abbott
Bradski G (2000) The openCV library. Dr Dobb’s Journal: Software Tools for the Professional Programmer. 25(11):120–123
Patro S, Sahu KK (2015) Normalization: A preprocessing stage. ar**v preprint ar**v:150306462
Hatfaludi C-A, Tache I-A, Ciușdel CF, Puiu A, Stoian D, Itu LM et al (2022) Towards a Deep-Learning Approach for Prediction of Fractional Flow Reserve from Optical Coherence Tomography. Appl Sci 12(14):6964
Santurkar S, Tsipras D, Ilyas A, Madry A (2018) How does batch normalization help optimization? Advances in neural information processing systems. ;31
Wong T-T (2015) Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recogn 48(9):2839–2846
Zhang Z (2018) Improved adam optimizer for deep neural networks. 2018 IEEE/ACM 26th international symposium on quality of service (IWQoS): Ieee; p. 1–2
Kline DM, Berardi VL (2005) Revisiting squared-error and cross-entropy functions for training neural network classifiers. Neural Comput Appl 14:310–318
Liashchynskyi P, Liashchynskyi P (2019) Grid search, random search, genetic algorithm: a big comparison for NAS. ar**v Preprint ar**v :191206059
Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G et al (2019) Pytorch: an imperative style, high-performance deep learning library. Adv Neural Inf Process Syst 32
Hoo ZH, Candlish J, Teare D (2017) What is an ROC curve? BMJ Publishing Group Ltd and the British Association for Accident, pp 357–359
Lobo JM, Jiménez-Valverde A, Real R (2008) AUC: a misleading measure of the performance of predictive distribution models. Glob Ecol Biogeogr 17(2):145–151
Unal I (2017) Defining an optimal cut-point value in ROC analysis: an alternative approach. Computational and mathematical methods in medicine. ;2017
Youden WJ (1950) Index for rating diagnostic tests. Cancer 3(1):32–35
Lakshminarayanan B, Pritzel A, Blundell C (2017) Simple and scalable predictive uncertainty estimation using deep ensembles. Adv Neural Inf Process Syst. ;30
Bote-Curiel L, Munoz-Romero S, Gerrero-Curieses A, Rojo-Álvarez JL (2019) Deep learning and big data in healthcare: a double review for critical beginners. Appl Sci 9(11):2331
Demir-Kavuk O, Kamada M, Akutsu T, Knapp E-W (2011) Prediction using step-wise L1, L2 regularization and feature selection for small data sets with large number of features. BMC Bioinformatics 12:1–10
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Wong SC, Gatt A, Stamatescu V, McDonnell MD (2016) Understanding data augmentation for classification: when to warp? 2016 international conference on digital image computing: techniques and applications (DICTA): IEEE; p. 1–6
Kumamaru KK, Fujimoto S, Otsuka Y, Kawasaki T, Kawaguchi Y, Kato E et al (2020) Diagnostic accuracy of 3D deep-learning-based fully automated estimation of patient-level minimum fractional flow reserve from coronary computed tomography angiography. Eur Heart Journal-Cardiovascular Imaging 21(4):437–445
Zreik M, van Hamersvelt RW, Khalili N, Wolterink JM, Voskuil M, Viergever MA et al (2019) Deep learning analysis of coronary arteries in cardiac CT angiography for detection of patients requiring invasive coronary angiography. IEEE Trans Med Imaging 39(5):1545–1557
Lyras KG, Lee J (2021) An improved reduced-order model for pressure drop across arterial stenoses. PLoS ONE 16(10):e0258047
Funding
The research leading to these results has received funding from the EEA Grants 2014–2021, under Project contract no. 33/2021. This work was supported by a grant of the Romanian National Authority for Scientific Research and Innovation, CCCDI – UEFISCDI, project number ERANET-PERMED-PROGRESS, within PNCDI III.
Author information
Authors and Affiliations
Contributions
Conceptualization, C.-A.H., I.-A.T., and L.M.I.; methodology, C.-A.H., C.F.C., I.-A.T., and A.P.; software, C.-A.H., A.P., and D.S.; validation, L.C., N.-M.P.-F., V.B., and A.S.-U.; formal analysis, C.F.C.; investigation, L.C., N.-M.P.-F., and V.B.; resources, I.-A.T. and L.M.I.; data curation, I.-A.T. and L.C.; writing—original draft preparation, C.-A.H., I.-A.T., and L.M.I.; writing—review and editing, C.F.C.; visualization, C.-A.H. and L.M.I.; supervision, L.M.I. and A.S.-U.; project administration, L.M.I. and A.S.-U.; funding acquisition, L.M.I. and A.S.-U. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hatfaludi, CA., Tache, IA., Ciusdel, CF. et al. Co-registered optical coherence tomography and X-ray angiography for the prediction of fractional flow reserve. Int J Cardiovasc Imaging 40, 1029–1039 (2024). https://doi.org/10.1007/s10554-024-03069-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10554-024-03069-z