Artificial intelligence in cardiovascular CT: Current status and future implications

Published:March 22, 2021DOI:https://doi.org/10.1016/j.jcct.2021.03.006

      Abstract

      Artificial intelligence (AI) refers to the use of computational techniques to mimic human thought processes and learning capacity. The past decade has seen a rapid proliferation of AI developments for cardiovascular computed tomography (CT). These algorithms aim to increase efficiency, objectivity, and performance in clinical tasks such as image quality improvement, structure segmentation, quantitative measurements, and outcome prediction. By doing so, AI has the potential to streamline clinical workflow, increase interpretative speed and accuracy, and inform subsequent clinical pathways. This review covers state-of-the-art AI techniques in cardiovascular CT and the future role of AI as a clinical support tool.

      Keywords

      To read this article in full you will need to make a payment

      References

        • Lin A.
        • Kolossváry M.
        • Išgum I.
        • Maurovich-Horvat P.
        • Slomka P.J.
        • Dey D.
        Artificial intelligence: improving the efficiency of cardiovascular imaging.
        Expet Rev Med Dev. 2020; 17: 565-577
        • Turing A.M.
        Computing machiner and intelligence.
        Mind. 1950; LIX: 433-460
        • Dey D.
        • Slomka P.J.
        • Leeson P.
        • et al.
        Artificial intelligence in cardiovascular imaging: JACC state-of-the-art review.
        J Am Coll Cardiol. 2019; 73: 1317-1335
        • Sudre C.H.
        • Li W.
        • Vercauteren T.
        • Ourselin S.
        • Jorge Cardoso M.
        Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations.
        in: Cardoso M. Lecture Notes in Computer Science. Springer, 2017: 240-248
        • Bradley A.P.
        The use of the area under the ROC curve in the evaluation of machine learning algorithms.
        Pattern Recogn. 1997; 30: 1145-1159
        • Wolterink J.M.
        • Leiner T.
        • Viergever M.A.
        • Isgum I.
        Generative adversarial networks for noise reduction in low-dose CT.
        IEEE Trans Med Imag. 2017; 36: 2536-2545
        • Chen H.
        • Zhang Y.
        • Zhang W.
        • et al.
        Low-dose CT via convolutional neural network.
        Biomed Opt Express. 2017; 8: 679-694
        • Kang E.
        • Min J.
        • Ye J.C.
        A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction.
        Med Phys. 2017; 44: e360-e375
        • Green M.
        • Marom E.M.
        • Konen E.
        • Kiryati N.
        • Mayer A.
        3-D neural denoising for low-dose coronary CT angiography (CCTA).
        Comput Med Imag Graph. 2018; 70: 185-191
        • Kang E.
        • Koo H.J.
        • Yang D.H.
        • Seo J.B.
        • Ye J.C.
        Cycle-consistent adversarial denoising network for multiphase coronary CT angiography.
        Med Phys. 2019; 46: 550-562
        • Lossau T.
        • Nickisch H.
        • Wissel T.
        • et al.
        Motion estimation and correction in cardiac CT angiography images using convolutional neural networks.
        Comput Med Imag Graph. 2019; 76: 101640
        • Jung S.
        • Lee S.
        • Jeon B.
        • Jang Y.
        • Chang H.
        Deep learning cross-phase style transfer for motion artifact correction in coronary computed tomography angiography.
        IEEE Access. 2020; 8: 81849-81863
        • Murphy D.J.
        • Lavelle L.P.
        • Gibney B.
        • O’Donohoe R.L.
        • Rémy-Jardin M.
        • Dodd J.D.
        Diagnostic accuracy of standard axial 64-slice chest CT compared to cardiac MRI for the detection of cardiomyopathies.
        Br J Radiol. 2016; 89 (20150810): 20150810
        • Greupner J.
        • Zimmermann E.
        • Grohmann A.
        • et al.
        Head-to-Head comparison of left ventricular function assessment with 64-row computed tomography, biplane left cineventriculography, and both 2- and 3-dimensional transthoracic echocardiography.
        J Am Coll Cardiol. 2012; 59: 1897
        • Bruns S.
        • Wolterink J.M.
        • Takx R.A.P.
        • et al.
        Deep learning from dual-energy information for whole-heart segmentation in dual-energy and single-energy non-contrast-enhanced cardiac CT.
        Med Phys. 2020; 47: 5048-5060
        • Zreik M.
        • Leiner T.
        • De Vos B.
        • van Hamersvelt R.
        • Viergever M.
        • Isgum I.
        Automatic segmentation of the left ventricle in cardiac CT angiography using convolutional neural networks.
        IEEE.Int. Symp. Biomed. Imag. 2016; : 40-43
        • Jun Guo B.
        • He X.
        • Lei Y.
        • et al.
        Automated left ventricular myocardium segmentation using 3D deeply supervised attention U-net for coronary computed tomography angiography; CT myocardium segmentation.
        Med Phys. 2020; 47: 1775-1785
        • Baskaran L.
        • Maliakal G.
        • Al’Aref S.J.
        • et al.
        Identification and quantification of cardiovascular structures from CCTA: an end-to-end, rapid, pixel-wise.
        Deep-Learning Method. JACC: Cardiovascular Imaging. 2020; 13: 1163-1171
        • Klein R.
        • Ametepe E.S.
        • Yam Y.
        • Dwivedi G.
        • Chow B.J.
        Cardiac CT assessment of left ventricular mass in mid-diastasis and its prognostic value.
        Eur Heart J Cardiovasc Imaging. 2017; 18: 95-102
        • Grbic S.
        • Ionasec R.
        • Vitanovski D.
        • et al.
        Complete valvular heart apparatus model from 4D cardiac CT.
        Med Image Anal. 2012; 16: 1003-1014
        • Liang L.
        • Kong F.
        • Martin C.
        • et al.
        Machine learning-based 3-D geometry reconstruction and modeling of aortic valve deformation using 3-D computed tomography images.
        Int J Numer Method Biomed Eng. 2017; 33https://doi.org/10.1002/cnm.2827
        • Al W.A.
        • Jung H.Y.
        • Yun I.D.
        • Jang Y.
        • Park H.-B.
        • Chang H.-J.
        Automatic aortic valve landmark localization in coronary CT angiography using colonial walk.
        PloS One. 2018; 13 (e0200317)e0200317
        • Zheng Y.
        • Barbu A.
        • Georgescu B.
        • Scheuering M.
        • Comaniciu D.
        Four-chamber heart modeling and automatic segmentation for 3-D cardiac CT volumes using marginal space learning and steerable features.
        IEEE Trans Med Imag. 2008; 27: 1668-1681
        • Lesage D.
        • Angelini E.D.
        • Bloch I.
        • Funka-Lea G.
        A review of 3D vessel lumen segmentation techniques: models, features and extraction schemes.
        Med Image Anal. 2009; 13: 819-845
        • Kelm B.M.
        • Mittal S.
        • Zheng Y.
        • et al.
        Detection, grading and classification of coronary stenoses in computed tomography angiography.
        Med Image Comput Comput Assist Interv. 2011; 14: 25-32
        • Gülsün M.
        • Funka-Lea G.
        • Sharma P.
        • Rapaka S.
        • Zheng Y.
        Coronary Centerline Extraction via Optimal Flow Paths and CNN Path Pruning.
        2016
        • Wolterink J.M.
        • van Hamersvelt R.W.
        • Viergever M.A.
        • Leiner T.
        • Isgum I.
        Coronary artery centerline extraction in cardiac CT angiography using a CNN-based orientation classifier.
        Med Image Anal. 2019; 51: 46-60
        • Wolterink J.
        • Leiner T.
        • Išgum I.
        Graph convolutional networks for coronary artery segmentation in cardiac CT angiography.
        in: International Workshop on Graph Learning in Medical Imaging. Springer, 2019: 62-69
        • Budoff M.J.
        • Young R.
        • Burke G.
        • et al.
        Ten-year association of coronary artery calcium with atherosclerotic cardiovascular disease (ASCVD) events: the multi-ethnic study of atherosclerosis (MESA).
        Eur Heart J. 2018; 39: 2401-2408
      1. Wolterink J, Leiner T, Takx R, Viergever M, Isgum I. An automatic machine learning system for coronary calcium scoring in clinical non-contrast enhanced, ECG-triggered cardiac CT. Vol vol. 9035. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 90352014.

        • Wolterink J.M.
        • Leiner T.
        • Takx R.A.
        • Viergever M.A.
        • Isgum I.
        Automatic coronary calcium scoring in non-contrast-enhanced ECG-triggered cardiac CT with ambiguity detection.
        IEEE Trans Med Imag. 2015; 34: 1867-1878
        • van Velzen S.G.M.
        • Lessmann N.
        • Velthuis B.K.
        • et al.
        Deep learning for automatic calcium scoring in CT: validation using multiple cardiac CT and chest CT protocols.
        Radiology. 2020; 295: 66-79
        • Lin A.
        • Dey D.
        • Wong D.T.L.
        • Nerlekar N.
        Perivascular adipose tissue and coronary atherosclerosis: from biology to imaging phenotyping.
        Curr Atherosclerosis Rep. 2019; 21: 47
        • Mahabadi A.A.
        • Berg M.H.
        • Lehmann N.
        • et al.
        Association of epicardial fat with cardiovascular risk factors and incident myocardial infarction in the general population: the Heinz Nixdorf Recall Study.
        J Am Coll Cardiol. 2013; 61: 1388-1395
        • Dey D.
        • Wong N.D.
        • Tamarappoo B.
        • et al.
        Computer-aided non-contrast CT-based quantification of pericardial and thoracic fat and their associations with coronary calcium and Metabolic Syndrome.
        Atherosclerosis. 2010; 209: 136-141
        • Goeller M.
        • Achenbach S.
        • Marwan M.
        • et al.
        Epicardial adipose tissue density and volume are related to subclinical atherosclerosis, inflammation and major adverse cardiac events in asymptomatic subjects.
        J Cardiovasc Comput Tomogr. 2018; 12: 67-73
        • Commandeur F.
        • Goeller M.
        • Razipour A.
        • et al.
        Fully automated CT quantification of epicardial adipose tissue by deep learning: a multicenter study.
        Radiology: Artif Intell. 2019; 1e190045
        • Arbab-Zadeh A.
        • Hoe J.
        Quantification of coronary arterial stenoses by multidetector CT angiography in comparison with conventional angiography methods, caveats, and implications.
        JACC Cardiovasc Imaging. 2011; 4: 191-202
        • Kang D.
        • Dey D.
        • Slomka P.J.
        • et al.
        Structured learning algorithm for detection of nonobstructive and obstructive coronary plaque lesions from computed tomography angiography.
        J Med Imaging. 2015; 2014003
        • Hong Y.
        • Commandeur F.
        • Cadet S.
        • et al.
        Deep learning-based stenosis quantification from coronary CT Angiography.
        Proc SPIE-Int Soc Opt Eng. 2019; 10949: 109492I
        • Driessen Roel S.
        • Danad I.
        • Stuijfzand Wijnand J.
        • et al.
        Comparison of coronary computed tomography angiography, fractional flow reserve, and perfusion imaging for ischemia diagnosis.
        J Am Coll Cardiol. 2019; 73: 161-173
        • Tesche C.
        • De Cecco C.N.
        • Albrecht M.H.
        • et al.
        Coronary CT angiography–derived fractional flow reserve.
        Radiology. 2017; 285: 17-33
        • Itu L.
        • Rapaka S.
        • Passerini T.
        • et al.
        A machine-learning approach for computation of fractional flow reserve from coronary computed tomography.
        J Appl Physiol. 1985; 121 (2016): 42-52
        • Coenen A.
        • Kim Y.H.
        • Kruk M.
        • et al.
        Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography-based fractional flow reserve: result from the MACHINE Consortium.
        Circ Cardiovasc Imaging. 2018; 11e007217
        • Tesche C.
        • Otani K.
        • De Cecco C.N.
        • et al.
        Influence of coronary calcium on diagnostic performance of machine learning CT-FFR: results from MACHINE registry.
        JACC Cardiovasc Imaging. 2020; 13: 760-770
        • Wynants L.
        • van Smeden M.
        • McLernon D.J.
        • et al.
        Three myths about risk thresholds for prediction models.
        BMC Med. 2019; 17: 192
        • Nakanishi R.
        • Slomka P.
        • Rios R.
        • et al.
        Mahine learning adds to clincial and CAC assessment in predicting 1-year CHD and CVD deaths.
        JACC Cardiovasc Imaging. 2020; 14 (In press): 615-625
        • Eisenberg E.
        • McElhinney Priscilla A.
        • Commandeur F.
        • et al.
        Deep learning–based quantification of epicardial adipose tissue volume and attenuation predicts major adverse cardiovascular events in asymptomatic subjects.
        Circulation: Cardiovascular Imaging. 2020; 13e009829
        • Tamarappoo B.K.
        • Lin A.
        • Commandeur F.
        • et al.
        Machine learning integration of circulating and imaging biomarkers for explainable patient-specific prediction of cardiac events: a prospective study.
        Atherosclerosis. 2020; 318: 76-82
        • Motwani M.
        • Dey D.
        • Berman D.S.
        • et al.
        Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis.
        Eur Heart J. 2017; 38: 500-507
        • Dey D.
        • Gaur S.
        • Ovrehus K.A.
        • et al.
        Integrated prediction of lesion-specific ischaemia from quantitative coronary CT angiography using machine learning: a multicentre study.
        Eur Radiol. 2018; 28: 2655-2664
        • Kwan A.
        • McElhinney P.
        • Tamarappoo B.
        • et al.
        Prediction of revascularization by coronary CT angiography using a machine learning ischemia risk score.
        Eur Radiol. 2020; 31 (In press): 1227-1235
        • Fonseca C.G.
        • Backhaus M.
        • Bluemke D.A.
        • et al.
        The Cardiac Atlas Project--an imaging database for computational modeling and statistical atlases of the heart.
        Bioinformatics. 2011; 27: 2288-2295