open access

Ahead of print
Original Article
Published online: 2021-08-02
Get Citation

Angiography-based coronary flow reserve: The feasibility of automatic computation by artificial intelligence

Qiuyang Zhao, Chunming Li, Miao Chu, Juan Luis Gutiérrez-Chico, Shengxian Tu
DOI: 10.5603/CJ.a2021.0087
·
Pubmed: 34355775

open access

Ahead of print
Original articles
Published online: 2021-08-02

Abstract

Background: Coronary flow reserve (CFR) has prognostic value in patients with coronary artery disease. However, its measurement is complex, and automatic methods for CFR computation are scarcely available. We developed an automatic method for CFR computation based on coronary angiography and assessed its feasibility.

Methods: Coronary angiographies from the Corelab database were annotated by experienced analysts. A convolutional neural network (CNN) model was trained for automatic segmentation of the main coronary arteries during contrast injection. The segmentation performance was evaluated using 5-fold cross-validation. Subsequently, the CNN model was implemented into a prototype software package for automatic computation of the CFR (CFRauto) and applied on a different sample of patients with angiographies performed both at rest and during maximal hyperemia, to assess the feasibility of CFRauto and its agreement with the manual computational method based on frame count (CFRmanual).

Results: Altogether, 137,126 images of 5913 angiographic runs from 2407 patients were used to develop and evaluate the CNN model. Good segmentation performance was observed. CFRauto was successfully computed in 136 out of 149 vessels (91.3%). The average analysis time to derive CFRauto was 18.1 ± 10.3 s per vessel. Moderate correlation (r = 0.51, p < 0.001) was observed between CFRauto and CFRmanual, with a mean difference of 0.12 ± 0.53.

Conclusions: Automatic computation of the CFR based on coronary angiography is feasible. This method might facilitate wider adoption of coronary physiology in the catheterization laboratory to assess microcirculatory function.

Abstract

Background: Coronary flow reserve (CFR) has prognostic value in patients with coronary artery disease. However, its measurement is complex, and automatic methods for CFR computation are scarcely available. We developed an automatic method for CFR computation based on coronary angiography and assessed its feasibility.

Methods: Coronary angiographies from the Corelab database were annotated by experienced analysts. A convolutional neural network (CNN) model was trained for automatic segmentation of the main coronary arteries during contrast injection. The segmentation performance was evaluated using 5-fold cross-validation. Subsequently, the CNN model was implemented into a prototype software package for automatic computation of the CFR (CFRauto) and applied on a different sample of patients with angiographies performed both at rest and during maximal hyperemia, to assess the feasibility of CFRauto and its agreement with the manual computational method based on frame count (CFRmanual).

Results: Altogether, 137,126 images of 5913 angiographic runs from 2407 patients were used to develop and evaluate the CNN model. Good segmentation performance was observed. CFRauto was successfully computed in 136 out of 149 vessels (91.3%). The average analysis time to derive CFRauto was 18.1 ± 10.3 s per vessel. Moderate correlation (r = 0.51, p < 0.001) was observed between CFRauto and CFRmanual, with a mean difference of 0.12 ± 0.53.

Conclusions: Automatic computation of the CFR based on coronary angiography is feasible. This method might facilitate wider adoption of coronary physiology in the catheterization laboratory to assess microcirculatory function.

Get Citation

Keywords

artificial intelligence, convolutional network, coronary flow reserve, X-ray angiography, coronary heart disease

About this article
Title

Angiography-based coronary flow reserve: The feasibility of automatic computation by artificial intelligence

Journal

Cardiology Journal

Issue

Ahead of print

Article type

Original Article

Published online

2021-08-02

DOI

10.5603/CJ.a2021.0087

Pubmed

34355775

Keywords

artificial intelligence
convolutional network
coronary flow reserve
X-ray angiography
coronary heart disease

Authors

Qiuyang Zhao
Chunming Li
Miao Chu
Juan Luis Gutiérrez-Chico
Shengxian Tu

References (33)
  1. Bech GJ, De Bruyne B, Pijls NH, et al. Fractional flow reserve to determine the appropriateness of angioplasty in moderate coronary stenosis: a randomized trial. Circulation. 2001; 103(24): 2928–2934.
  2. De Bruyne B, Pijls NHJ, Kalesan B, et al. FAME 2 Trial Investigators. Fractional flow reserve-guided PCI versus medical therapy in stable coronary disease. N Engl J Med. 2012; 367(11): 991–1001.
  3. Tonino P, Bruyne BDe, Pijls N, et al. Fractional flow reserve versus angiography for guiding percutaneous coronary intervention. N Engl J Med. 2009; 360(3): 213–224.
  4. Driessen RS, Raijmakers PG, Stuijfzand WJ, et al. Myocardial perfusion imaging with PET. Int J Cardiovasc Imaging. 2017; 33(7): 1021–1031.
  5. Doucette JW, Corl PD, Payne HM, et al. Validation of a Doppler guide wire for intravascular measurement of coronary artery flow velocity. Circulation. 1992; 85(5): 1899–1911.
  6. Barbato E, Aarnoudse W, Aengevaeren WR, et al. Week 25 study group. Validation of coronary flow reserve measurements by thermodilution in clinical practice. Eur Heart J. 2004; 25(3): 219–223.
  7. Pijls NHJ, De Bruyne B, Smith L, et al. Coronary thermodilution to assess flow reserve: validation in humans. Circulation. 2002; 105(21): 2482–2486.
  8. Lee JM, Jung JH, Hwang D, et al. Coronary flow reserve and microcirculatory resistance in patients with intermediate coronary stenosis. J Am Coll Cardiol. 2016; 67(10): 1158–1169.
  9. Stegehuis VE, Wijntjens GWM, van de Hoef TP, et al. Distal Evaluation of Functional performance with Intravascular sensors to assess the Narrowing Effect-combined pressure and Doppler FLOW velocity measurements (DEFINE-FLOW) trial: Rationale and trial design. Am Heart J. 2020; 222: 139–146.
  10. Ahn SG, Suh J, Hung OY, et al. Discordance between fractional flow reserve and coronary flow reserve: insights from intracoronary imaging and physiological assessment. JACC Cardiovasc Interv. 2017; 10(10): 999–1007.
  11. Lee HS, Lee JM, Nam CW, et al. Consensus document for invasive coronary physiologic assessment in Asia-Pacific countries. Cardiol J. 2019; 26(3): 215–225.
  12. Douglas PS, Pontone G, Hlatky MA, et al. Clinical outcomes of fractional flow reserve by computed tomographic angiography-guided diagnostic strategies vs. usual care in patients with suspected coronary artery disease: the prospective longitudinal trial of FFR(CT): outcome and resource impacts study. Eur Heart J. 2015; 36(47): 3359–3367.
  13. Tu S, Barbato E, Köszegi Z, et al. 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 Interv. 2014; 7(7): 768–777.
  14. Tu S, Westra J, Yang J, et al. FAVOR Pilot Trial Study Group. Diagnostic Accuracy of Fast Computational Approaches to Derive Fractional Flow Reserve From Diagnostic Coronary Angiography: The International Multicenter FAVOR Pilot Study. JACC Cardiovasc Interv. 2016; 9(19): 2024–2035.
  15. Gutiérrez-Chico JL, Chen Y, Yu W, et al. Diagnostic accuracy and reproducibility of optical flow ratio for functional evaluation of coronary stenosis in a prospective series. Cardiol J. 2020; 27(4): 350–361.
  16. Huang J, Emori H, Ding D, et al. Comparison of Diagnostic Performance of Intracoronary Optical Coherence Tomography-based and Angiography-based Fractional Flow Reserve for Evaluation of Coronary Stenosis. Eurointervention: Journal of Europcr in Collaboration with the Working Group on Interventional Cardiology of the European Society of Cardiology. 2020.
  17. Yu W, Huang J, Jia D, et al. Diagnostic accuracy of intracoronary optical coherence tomography-derived fractional flow reserve for assessment of coronary stenosis severity. EuroIntervention. 2019; 15(2): 189–197.
  18. Yu W, Tanigaki T, Ding D, et al. TCT CONNECT-202 Diagnostic Accuracy of Novel Ultrasonic Flow Ratio in Identifying Hemodynamical Significance of Coronary Stenosis. J Am Coll Cardiol. 2020; 76(17): B86.
  19. De Maria GL, Scarsini R, Shanmuganathan M, et al. Angiography-derived index of microcirculatory resistance as a novel, pressure-wire-free tool to assess coronary microcirculation in ST elevation myocardial infarction. Int J Cardiovasc Imaging. 2020; 36(8): 1395–1406.
  20. Tebaldi M, Biscaglia S, Di Girolamo D, et al. Angio-Based index of microcirculatory resistance for the assessment of the coronary resistance: a proof of concept study. J Interv Cardiol. 2020; 2020: 8887369.
  21. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Lecture Notes in Computer Science. 2015: 234–241.
  22. Milletari F, Navab N, Ahmadi SA. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. 2016 Fourth International Conference on 3D Vision (3DV). 2016.
  23. Lin TY, Goyal P, Girshick R, et al. Focal Loss for Dense Object Detection. 2017 IEEE International Conference on Computer Vision (ICCV). 2017: 2980–2988.
  24. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv. 2014; 14126980.
  25. Zhang Y, Zhang Su, Westra J, et al. Automatic coronary blood flow computation: validation in quantitative flow ratio from coronary angiography. Int J Cardiovasc Imaging. 2019; 35(4): 587–595.
  26. TIMI Study Group. The Thrombolysis in Myocardial Infarction (TIMI) trial. Phase I findings. N Engl J Med. 1985; 312(14): 932–936.
  27. Davies J, Sen S, Dehbi HM, et al. Use of the instantaneous wave-free ratio or fractional flow reserve in PCI. N Engl J Med. 2017; 376(19): 1824–1834.
  28. Götberg M, Christiansen EH, Gudmundsdottir IJ, et al. Instantaneous wave-free ratio versus fractional flow reserve to guide PCI. N Engl J Med. 2017; 376(19): 1813–1823.
  29. Nasr-Esfahani E, Karimi N, Jafari MH, et al. Segmentation of vessels in angiograms using convolutional neural networks. Biomedical Signal Processing and Control. 2018; 40: 240–251.
  30. Fan J, Yang J, Wang Y, et al. Multichannel fully convolutional network for coronary artery segmentation in X-ray angiograms. IEEE Access. 2018; 6: 44635–44643.
  31. Yang Su, Kweon J, Roh JH, et al. Deep learning segmentation of major vessels in X-ray coronary angiography. Sci Rep. 2019; 9(1): 16897.
  32. Wu P, Gutiérrez-Chico JL, Tauzin H, et al. Automatic stent reconstruction in optical coherence tomography based on a deep convolutional model. Biomed Opt Express. 2020; 11(6): 3374–3394.
  33. Huang J, Emori H, Ding D, et al. Diagnostic performance of intracoronary optical coherence tomography-based versus angiography-based fractional flow reserve for the evaluation of coronary lesions. EuroIntervention. 2020; 16(7): 568–576.

Important: This website uses cookies. More >>

The cookies allow us to identify your computer and find out details about your last visit. They remembering whether you've visited the site before, so that you remain logged in - or to help us work out how many new website visitors we get each month. Most internet browsers accept cookies automatically, but you can change the settings of your browser to erase cookies or prevent automatic acceptance if you prefer.

By "Via Medica sp. z o.o." sp.k., ul. Świętokrzyska 73, 80–180 Gdańsk, Poland
tel.:+48 58 320 94 94, fax:+48 58 320 94 60, e-mail: viamedica@viamedica.pl