Technical note| Volume 107, 102555, March 2023

Download started.


Automated identification of myocardial perfusion defects in dynamic cardiac computed tomography using deep learning

  • Yoon-Chul Kim
    Division of Digital Healthcare, College of Software and Digital Healthcare Convergence, Yonsei University, Wonju, South Korea
    Search for articles by this author
  • Author Footnotes
    1 ORCID: 0000-0002-9983-048X.
    Yeon Hyeon Choe
    Corresponding author at: Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul 06351, South Korea.
    1 ORCID: 0000-0002-9983-048X.
    Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, South Korea
    Search for articles by this author
  • Author Footnotes
    1 ORCID: 0000-0002-9983-048X.
Published:March 04, 2023DOI:


      • A method for detection of perfusion defect in dynamic CT is presented.
      • Deep learning automates generation of myocardial blood flow maps.
      • Color-coded maps are used as input to model training and validation.
      • Cross-validation demonstrates high AUCs in identifying lesion location.



      The purpose of this study was to develop and evaluate deep convolutional neural network (CNN) models for quantifying myocardial blood flow (MBF) as well as for identifying myocardial perfusion defects in dynamic cardiac computed tomography (CT) images.


      Adenosine stress cardiac CT perfusion data acquired from 156 patients having or being suspected with coronary artery disease were considered for model development and validation. U-net-based deep CNN models were developed to segment the aorta and myocardium and to localize anatomical landmarks. Color-coded MBF maps were obtained in short-axis slices from the apex to the base level and were used to train a deep CNN classifier. Three binary classification models were built for the detection of perfusion defect in the left anterior descending artery (LAD), the right coronary artery (RCA), and the left circumflex artery (LCX) territories.


      Mean Dice scores were 0.94 (±0.07) and 0.86 (±0.06) for the aorta and myocardial deep learning-based segmentations, respectively. With the localization U-net, mean distance errors were 3.5 (±3.5) mm and 3.8 (±2.4) mm for the basal and apical center points, respectively. The classification models identified perfusion defects with the accuracy of mean area under the receiver operating curve (AUROC) values of 0.959 (±0.023) for LAD, 0.949 (±0.016) for RCA, and 0.957 (±0.021) for LCX.


      The presented method has the potential to fully automate the quantification of MBF and subsequently identify the main coronary artery territories with myocardial perfusion defects in dynamic cardiac CT perfusion.


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

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Physica Medica: European Journal of Medical Physics
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Assen M.V.
        • Vonder M.
        • Pelgrim G.J.
        • Von Knebel Doeberitz P.L.
        • Vliegenthart R.
        Computed tomography for myocardial characterization in ischemic heart disease: a state-of-the-art review.
        Eur Radiol Exp. 2020; 4: 36
        • Rossi A.
        • Merkus D.
        • Klotz E.
        • Mollet N.
        • de Feyter P.J.
        • Krestin G.P.
        Stress myocardial perfusion: imaging with multidetector CT.
        Radiology. 2014; 270: 25-46
        • Min J.K.
        • Leipsic J.
        • Pencina M.J.
        • Berman D.S.
        • Koo B.-K.
        • van Mieghem C.
        • et al.
        Diagnostic accuracy of fractional flow reserve from anatomic CT angiography.
        JAMA. 2012; 308: 1237
        • Coenen A.
        • Lubbers M.M.
        • Kurata A.
        • Kono A.
        • Dedic A.
        • Chelu R.G.
        • et al.
        Fractional flow reserve computed from noninvasive CT angiography data: diagnostic performance of an on-site clinician-operated computational fluid dynamics algorithm.
        Radiology. 2015; 274: 674-683
        • van Hamersvelt R.W.
        • Voskuil M.
        • de Jong P.A.
        • Willemink M.J.
        • Išgum I.
        • Leiner T.
        Diagnostic performance of on-site coronary CT angiography-derived fractional flow reserve based on patient-specific lumped parameter models.
        Radiol Cardiothorac Imaging. 2019; 1: e190036
        • Varga-Szemes A.
        • Meinel F.G.
        • De Cecco C.N.
        • Fuller S.R.
        • Bayer R.R.
        • Schoepf U.J.
        CT myocardial perfusion imaging.
        Am J Roentgenol. 2015; 204: 487-497
        • Avanzo M.
        • Porzio M.
        • Lorenzon L.
        • Milan L.
        • Sghedoni R.
        • Russo G.
        • et al.
        Artificial intelligence applications in medical imaging: A review of the medical physics research in Italy.
        Phys Med. 2021; 83: 221-241
        • Litjens G.
        • Ciompi F.
        • Wolterink J.M.
        • de Vos B.D.
        • Leiner T.
        • Teuwen J.
        • et al.
        State-of-the-Art deep learning in cardiovascular image analysis.
        JACC Cardiovasc Imaging. 2019; 12: 1549-1565
        • Sermesant M.
        • Delingette H.
        • Cochet H.
        • Jaïs P.
        • Ayache N.
        Applications of artificial intelligence in cardiovascular imaging.
        Nat Rev Cardiol. 2021; 18: 600-609
        • Zreik M.
        • Lessmann N.
        • van Hamersvelt R.W.
        • Wolterink J.M.
        • Voskuil M.
        • Viergever M.A.
        • et al.
        Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis.
        Med Image Anal. 2018; 44: 72-85
        • Wolterink J.M.
        • Leiner T.
        • de Vos B.D.
        • van Hamersvelt R.W.
        • Viergever M.A.
        • Isgum I.
        Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks.
        Med Image Anal. 2016; 34: 123-136
        • de Vos B.D.
        • Wolterink J.M.
        • Leiner T.
        • de Jong P.A.
        • Lessmann N.
        • Isgum I.
        Direct automatic coronary calcium scoring in cardiac and chest CT.
        IEEE Trans Med Imaging. 2019; 38: 2127-2138
        • Wolterink J.M.
        • Leiner T.
        • Viergever M.A.
        • Isgum I.
        Generative adversarial networks for noise reduction in low-dose CT.
        IEEE Trans Med Imaging. 2017; 36: 2536-2545
        • Lossau T.
        • Nickisch H.
        • Wissel T.
        • Bippus R.
        • Schmitt H.
        • Morlock M.
        • et al.
        Motion artifact recognition and quantification in coronary CT angiography using convolutional neural networks.
        Med Image Anal. 2019; 52: 68-79
        • Lossau (née Elss) T.
        • Nickisch H.
        • Wissel T.
        • Bippus R.
        • Schmitt H.
        • Morlock M.
        • et al.
        Motion estimation and correction in cardiac CT angiography images using convolutional neural networks.
        Comput Med Imaging Graph. 2019; 76: 101640
        • Ebersberger U.
        • Marcus R.P.
        • Schoepf U.J.
        • Lo G.G.
        • Wang Y.
        • Blanke P.
        • et al.
        Dynamic CT myocardial perfusion imaging: performance of 3D semi-automated evaluation software.
        Eur Radiol. 2014; 24: 191-199
        • Betancur J.
        • Commandeur F.
        • Motlagh M.
        • Sharir T.
        • Einstein A.J.
        • Bokhari S.
        • et al.
        Deep learning for prediction of obstructive disease from fast myocardial perfusion SPECT: A multicenter study.
        JACC Cardiovasc Imaging. 2018; 11: 1654-1663
        • Juarez-Orozco L.E.
        • Martinez-Manzanera O.
        • Storti A.E.
        • Knuuti J.
        Machine learning in the evaluation of myocardial ischemia through nuclear cardiology.
        Curr Cardiovasc Imaging Reports. 2019; 12: 5
        • Apostolopoulos I.D.
        • Apostolopoulos D.I.
        • Spyridonidis T.I.
        • Papathanasiou N.D.
        • Panayiotakis G.S.
        Multi-input deep learning approach for Cardiovascular Disease diagnosis using Myocardial Perfusion Imaging and clinical data.
        Phys Med. 2021; 84: 168-177
        • Monti C.B.
        • Codari M.
        • van Assen M.
        • De Cecco C.N.
        • Vliegenthart R.
        Machine learning and deep neural networks applications in computed tomography for coronary artery disease and myocardial perfusion.
        J Thorac Imaging. 2020; 35: S58-S65
        • Lara Hernandez K.A.
        • Rienmüller T.
        • Baumgartner D.
        • Baumgartner C.
        Deep learning in spatiotemporal cardiac imaging: A review of methodologies and clinical usability.
        Comput Biol Med. 2021; 130: 104200
        • Ho N.
        • Kim Y.C.
        Evaluation of transfer learning in deep convolutional neural network models for cardiac short axis slice classification.
        Sci Rep. 2021; 11: 1839
        • Kim Y.-C.
        • Kim K.R.
        • Choe Y.H.
        Automatic myocardial segmentation in dynamic contrast enhanced perfusion MRI using Monte Carlo dropout in an encoder-decoder convolutional neural network.
        Comput Methods Programs Biomed. 2020; 185: 105150
        • Lewis M.A.
        • Pascoal A.
        • Keevil S.F.
        • Lewis C.A.
        Selecting a CT scanner for cardiac imaging: the heart of the matter.
        Br J Radiol. 2016; 89: 20160376
        • Takafuji M.
        • Kitagawa K.
        • Ishida M.
        • Goto Y.
        • Nakamura S.
        • Nagasawa N.
        • et al.
        Myocardial coverage and radiation dose in dynamic myocardial perfusion imaging using third-generation dual-source CT.
        Korean J Radiol. 2020; 21: 58
        • Yaniv Z.
        • Lowekamp B.C.
        • Johnson H.J.
        • Beare R.
        SimpleITK image-analysis notebooks: a collaborative environment for education and reproducible research.
        J Digit Imaging. 2018; 31: 290-303
        • Ronneberger O.
        • Fischer P.
        • U-net B.T.
        Convolutional networks for biomedical image segmentation.
        in: International conference on medical image computing and computer-assisted intervention. Springer, 2015: 234-241
        • Payer C.
        • Stern D.
        • Bischof H.
        • Urschler M.
        Integrating spatial configuration into heatmap regression based CNNs for landmark localization.
        Med Image Anal. 2019; 54: 207-219
        • Ishida M.
        • Kitagawa K.
        • Ichihara T.
        • Natsume T.
        • Nakayama R.
        • Nagasawa N.
        • et al.
        Underestimation of myocardial blood flow by dynamic perfusion CT: Explanations by two-compartment model analysis and limited temporal sampling of dynamic CT.
        J Cardiovasc Comput Tomogr. 2016; 10: 207-214
        • Bamberg F.
        • Klotz E.
        • Flohr T.
        • Becker A.
        • Becker C.R.
        • Schmidt B.
        • et al.
        Dynamic myocardial stress perfusion imaging using fast dual-source CT with alternating table positions: initial experience.
        Eur Radiol. 2010; 20: 1168-1173
        • van Assen M.
        • Pelgrim G.J.
        • De Cecco C.N.
        • Stijnen J.M.A.
        • Zaki B.M.
        • Oudkerk M.
        • et al.
        Intermodel disagreement of myocardial blood flow estimation from dynamic CT perfusion imaging.
        Eur J Radiol. 2019; 110: 175-180
        • Kikuchi Y.
        • Oyama-Manabe N.
        • Naya M.
        • Manabe O.
        • Tomiyama Y.
        • Sasaki T.
        • et al.
        Quantification of myocardial blood flow using dynamic 320-row multi-detector CT as compared with (1)(5)O-H(2)O PET.
        Eur Radiol. 2014; 24: 1547-1556
        • Pedregosa F.
        • Varoquaux G.
        • Gramfort A.
        • Michel V.
        • Thirion B.
        • Grisel O.
        • et al.
        Scikit-learn: Machine learning in Python.
        J Mach Learn Res. 2011; 12: 2825-2830
        • Wichmann J.L.
        • Meinel F.G.
        • Schoepf U.J.
        • Lo G.G.
        • Choe Y.H.
        • Wang Y.
        • et al.
        Absolute versus relative myocardial blood flow by dynamic CT myocardial perfusion imaging in patients with anatomic coronary artery disease.
        Am J Roentgenol. 2015; 205: W67-W72