Deep Learning-based Quantitative CT Myocardial Perfusion Imaging and Risk Stratification of Coronary Artery Disease.

Journal: Radiology
PMID: 40298595

Abstract

Background Precise assessment of myocardial ischemia burden and cardiovascular risk stratification based on dynamic CT myocardial perfusion imaging (MPI) is lacking. Purpose To develop and validate a deep learning (DL) model for automated quantification of myocardial blood flow (MBF) and ischemic myocardial volume (IMV) percentage and to explore the prognostic value for major adverse cardiovascular events (MACE). Materials and Methods This multicenter study comprised three cohorts of patients with clinically indicated CT MPI and coronary CT angiography (CCTA). Cohorts 1 and 2 were retrospective cohorts (May 2021 to June 2023 and January 2018 to December 2022, respectively). Cohort 3 was prospectively included (November 2016 to December 2021). The DL model was developed in cohort 1 (training set: 211 patients, validation set: 57 patients, test set: 90 patients). The diagnostic performance of MBF derived from the DL model (MBF) for myocardial ischemia was evaluated in cohort 2 based on the area under the receiver operating characteristic curve (AUC). The prognostic value of the DL model-derived IMV percentage was assessed in cohort 3 using multivariable Cox regression analyses. Results Across three cohorts, 1108 patients (mean age: 61 years ± 12 [SD]; 667 men) were included. MBF showed excellent agreement with manual measurements in the test set (segment-level intraclass correlation coefficient = 0.928; 95% CI: 0.921, 0.935). MBF showed higher diagnostic performance (vessel-based AUC: 0.97) over CT-derived fractional flow reserve (FFR) (vessel-based AUC: 0.87; = .006) and CCTA-derived diameter stenosis (vessel-based AUC: 0.79; < .001) for hemodynamically significant lesions, compared with invasive FFR. Over a mean follow-up of 39 months, MACE occurred in 94 (14.2%) of 660 patients. IMV percentage was an independent predictor of MACE (hazard ratio = 1.12, = .003), with incremental prognostic value (C index: 0.86; 95% CI: 0.84, 0.88) over conventional risk factors and CCTA parameters (C index: 0.84; 95% CI: 0.82, 0.86; = .02). Conclusion A DL model enabled automated CT MBF quantification and accurate diagnosis of myocardial ischemia. DL model-derived IMV percentage was an independent predictor of MACE and mildly improved cardiovascular risk stratification. © RSNA, 2025 See also the editorial by Zhu and Xu in this issue.

Authors

  • Yarong Yu
    Department of Radiology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, #85 Wujin Rd, Shanghai, 200080, China.
  • Dijia Wu
  • Jiajun Yuan
    Shanghai Engineering Research Center of Intelligence Pediatrics (SERCIP), Shanghai, 200127, People's Republic of China.
  • Lihua Yu
    From the Departments of Radiology (M.L., LY., J.Z.) and Cardiology (W.Y.), Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, 85 Wujin Rd, Shanghai 200080, China; Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, China (R.L.); and Shanghai United Imaging Intelligence, Shanghai, China (Z.C., D.W.).
  • Xu Dai
    From the Institute of Diagnostic and Interventional Radiology (Y.L., M.Y., X.D., J.Z.) and Department of Cardiology (Z.L., C.S.), Shanghai Jiao Tong University Affiliated Sixth People's Hospital, #600, Yishan Rd, Shanghai, China 200233; Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China (Y.W.); and Department of Radiology, Fuwai Hospital, State Key Laboratory of Cardiovascular Disease, National Centre for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China (B.L.).
  • Wenli Yang
    Discipline of Information & Communication Technology, School of Technology, Environments & Design, University of Tasmania Sandy Bay Campus, Launceston, Australia. yang.wenli@utas.edu.au.
  • Ziting Lan
    Department of Radiology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, #85 Wujin Rd, Shanghai, China 200080.
  • Jiayu Wang
    Department of Cardiology, the Second Hospital of Shandong University, 250033 Jinan, Shandong, China.
  • Ze Tao
    Shanghai United Imaging Intelligence, Shanghai, China.
  • Yiqiang Zhan
  • Runjianya Ling
    From the Departments of Radiology (M.L., LY., J.Z.) and Cardiology (W.Y.), Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, 85 Wujin Rd, Shanghai 200080, China; Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, China (R.L.); and Shanghai United Imaging Intelligence, Shanghai, China (Z.C., D.W.).
  • Xiaomei Zhu
    Key Laboratory of Optical Technology and Instrument for Medicine, Ministry of Education, School of Optical-Electrical Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
  • Yi Xu
    School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, PR China.
  • Yuehua Li
    From the Institute of Diagnostic and Interventional Radiology (Y.L., M.Y., X.D., J.Z.) and Department of Cardiology (Z.L., C.S.), Shanghai Jiao Tong University Affiliated Sixth People's Hospital, #600, Yishan Rd, Shanghai, China 200233; Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China (Y.W.); and Department of Radiology, Fuwai Hospital, State Key Laboratory of Cardiovascular Disease, National Centre for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China (B.L.).
  • Jiayin Zhang
    Department of Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, China.

Keywords

External Resources

Popular Topics
Recent Journals