Skip to main content

Advertisement

SpringerLink
Log in

A 2-year investigation of the impact of the computed tomography–derived fractional flow reserve calculated using a deep learning algorithm on routine decision-making for coronary artery disease management

  • Imaging Informatics and Artificial Intelligence
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objective

This study aims to investigate the safety and feasibility of using a deep learning algorithm to calculate computed tomography angiography–based fractional flow reserve (DL-FFRCT) as an alternative to invasive coronary angiography (ICA) in the selection of patients for coronary intervention.

Materials and methods

Patients (N = 296) with symptomatic coronary artery disease identified by coronary computed tomography angiography (CTA) with stenosis over 50% were retrospectively enrolled from a single centre in this study. ICA-guided interventions were performed in patients at admission, and DL-FFRCT was conducted retrospectively. The influences on decision-making by using DL-FFRCT and the clinical outcome were compared to those of ICA-guided care for symptomatic CAD at the 2-year follow-up evaluation.

Result

Two hundred forty-three patients were evaluated. Up to 72% of diagnostic ICA studies could have been avoided by using a DL-FFRCT value > 0.8 as a cut-off for intervention. A similar major adverse cardiovascular event (MACE) rate was observed in patients who underwent revascularisation with a DL-FFRCT value ≤ 0.8 (2.9%) compared to that of ICA-guided interventions (3.3%) (stented lesions with ICA stenosis > 75%) (p = 0.838).

Conclusion

DL-FFRCT can reduce the need for diagnostic coronary angiography when identifying patients suitable for coronary intervention. A low MACE rate was found in a 2-year follow-up investigation.

Key Points

• Seventy-two percent of diagnostic ICA studies could have been avoided by using a DL-FFRCT value > 0.8 as a cut-off for intervention.

• Coronary artery stenting based on the diagnosis by using a 320-detector row CT scanner and a positive DL-FFRCT value could potentially be associated with a lower occurrence rate of major adverse cardiovascular events (2.9%) within the first 2 years.

• A low event rate was found when intervention was performed in tandem lesions with haemodynamic significance based on DL-FFRCT < 0.8 as a cut-off value.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Abbreviations

CABG:

Coronary artery bypass surgery

CAD:

Coronary artery disease

CCTA:

Coronary computed tomography angiography

CFD:

Computed fluid dynamics

DL-FFRCT:

Deep learning–based FFRCT

FFR:

Fractional flow reserve

FFRCT:

Coronary computed tomography angiography (CCTA)-derived fractional flow reserve

ICA:

Invasive coronary angiography

LAD:

Left anterior descending artery

MACEs:

Major adverse cardiovascular events

References

  1. Patel MR, Nørgaard BL, Fairbairn TA et al (2019) 1-year impact on medical practice and clinical outcomes of FFRCT. JACC Cardiovasc Imaging:2978

  2. Douglas PS, De Bruyne B, Pontone G et al (2016) 1-year outcomes of FFRCT-guided care in patients with suspected coronary disease. J Am Coll Cardiol 68(5):435

  3. Tanaka K et al (2016) Comparison between non-invasive (coronary computed tomography angiography derived) and invasive-fractional flow reserve in patients with serial stenoses within one coronary artery: a NXT trial substudy. Ann Biomed Eng 44(2):580–589

    Article  Google Scholar 

  4. Tesche C et al (2018) Coronary CT angiography–derived fractional flow reserve: machine learning algorithm versus computational fluid dynamics modeling. Radiology 288(1):64–72

    Article  Google Scholar 

  5. Coenen A et al (2018) Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography–based fractional flow reserve. Circ Cardiovasc Imaging 11(6):e007217

    Article  Google Scholar 

  6. Tesche C et al (2019) Influence of coronary calcium on diagnostic performance of machine learning CT-FFR: results from MACHINE registry. JACC Cardiovasc Imaging

  7. Qiao HY et al (2020) Impact of machine learning–based coronary computed tomography angiography fractional flowreserve on treatment decisions and clinical outcomes in patients with suspected coronary artery disease. Eur Radiol 30(11):5841–5851

  8. Scanlon Patrick J et al (1999) ACC/AHA guidelines for coronary angiography: executive summary and recommendations. Circulation 99(17):2345–2357

    Article  Google Scholar 

  9. Liu X et al (2019) Evaluation of fractional flow reserve in patients with stable angina: can CT compete with angiography? Eur Radiol 29(7):3669–3677

    Article  Google Scholar 

  10. Gao Z, Wang X, Sun S et al (2020) Learning physical properties in complex visual scenes: An intelligent machine for perceiving blood flow dynamics from static CT angiography imaging. Neural Netw 123:82–93

  11. Kim HJ et al (2010) Patient-specific modeling of blood flow and pressure in human coronary arteries. Ann Biomed Eng 38(10):3195–3209

    Article  CAS  Google Scholar 

  12. Tu S et al (2014) Fractional flow reserve calculation from 3-dimensional quantitative coronary angiography and TIMI frame counta fast computer model to quantify the functional significance of moderately obstructed coronary arteries. J Am Coll Cardiol Intv 7(7):768–777

    Article  Google Scholar 

  13. Xu P et al (2018) Assessment of boundary conditions for CFD simulation in human carotid artery. Biomech Model Mechanobiol 17(6):1581–1597

    Article  Google Scholar 

  14. Gao Z et al (2017) Automatic segmentation of coronary tree in CT angiography images. Int J Adapt Control and Signal Process. https://doi.org/10.1002/acs.2762

  15. Liu X et al (2017) Hemodynamics analysis of the serial stenotic coronary arteries. Biomed Eng Online 16(1):127

    Article  Google Scholar 

  16. Wang X et al (2018) Functional assessment of stenotic coronary artery in 3D geometric reconstruction from fusion of intravascular ultrasound and x-ray angiography. IEEE Access 6:53330–53341

    Article  Google Scholar 

  17. Tonino PAL et al (2010) Angiographic versus functional severity of coronary artery stenoses in the FAME study. J Am Coll Cardiol 55(25):2816

    Article  Google Scholar 

  18. Hlatky MA et al (2015) Quality-of-life and economic outcomes of assessing fractional flow reserve with computed tomography angiography. J Am Coll Cardiol 66(21):2315

    Article  Google Scholar 

  19. Douglas PS et al (2015) 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 FFRCT: outcome and resource impacts study. Eur Heart J 36(47):3359–3367

    Article  CAS  Google Scholar 

  20. investigators TS-H (2015) CT coronary angiography in patients with suspected angina due to coronary heart disease (SCOT-HEART): an open-label, parallel-group, multicentre trial. Lancet 385(9985):2383–2391

    Article  Google Scholar 

  21. Fairbairn TA et al (2018) Real-world clinical utility and impact on clinical decision-making of coronary computed tomography angiography-derived fractional flow reserve: lessons from the ADVANCE Registry. Eur Heart J 39(41):3701–3711

    Article  Google Scholar 

  22. Lu MT et al (2017) Noninvasive FFR derived from coronary CT angiography management and outcomes in the PROMISE trial. JACC Cardiovasc Imaging 10(11):1350

    Article  Google Scholar 

  23. Jensen JM et al (2017) Computed tomography derived fractional flow reserve testing in stable patients with typical angina pectoris: influence on downstream rate of invasive coronary angiography. Eur Heart J Cardiovasc Imaging 19(4):405–414

    Article  Google Scholar 

  24. Xu PP et al (2020) The influence of image quality on diagnostic performance of a machine learning–based fractional flow reserve derived from coronary CT angiography. Eur Radiol 30(5):2525–2534

    Article  Google Scholar 

  25. West AM, Beller GA (2010) 256-and 320-row coronary CTA: is more better? Oxford University Press

  26. Hsiao EM, Rybicki FJ, Steigner M (2010) CT coronary angiography: 256-slice and 320-detector row scanners. Curr Cardiol Rep 12(1):68–75

    Article  Google Scholar 

  27. Tesche C, Gray HN (2020) Machine learning and deep neural networks applications in coronary flow assessment: the case of computed tomography fractional flow reserve. J Thorac Imaging 35

  28. Modi BN et al (2019) Predicting the physiological effect of revascularisation in serially diseased coronary arteries. Circ Cardiovasc Interv 12(2):e007577

    Article  Google Scholar 

  29. Sakuma H (2019) Coronary CT angiography fractional flow reserve analysis: a practical tool or a luxury for research centers? Radiology 292(3):606–607

  30. Packard RRS et al (2016) Fractional flow reserve by computerised tomography and subsequent coronary revascularisation. Eur Heart J Cardiovasc Imaging 18(2):145–152

    Article  Google Scholar 

  31. Gaur S et al (2016) Coronary plaque quantification and fractional flow reserve by coronary computed tomography angiography identify ischaemia-causing lesions. Eur Heart J 37(15):1220–1227

    Article  Google Scholar 

Download references

Acknowledgements

We thank the clinical support by Dr. Zeyu Xiao. We thank Keya medical (Shenzhen, Guangdong, China) for providing the support of deep learning-based CT-FFR product.

Funding

This study is supported by grand from Guangzhou Science and Technology Plan Project (Grant Number: 201807010046), Guangzhou Key Laboratory of Molecular and Functional Imaging for Clinical Translation (Grant Number:201905010003), Natural Science Foundation of Guangdong Province, China (Grant Number: 2019A1515011463), the Science and Technology Planning Project of Guangdong Province, China (Grant Number: 2018A050506031, 2019B010110001), the National Natural Science Foundation of China (Grant Number: 61771464, U1801265, 82001910), and Medical Scientific Research Foundation of Guangdong Province of China (Grant Number: A2018132).

Author information

Author notes

  1. Xin Liu and Xukai Mo contributed equally to this work.

Authors and Affiliations

  1. Guangdong Academy Research on VR Industry, Foshan University, #18 Jiangwan 1st Road, Foshan, 528000, Guangdong, China

    Xin Liu

  2. Medical Imaging Center, The First Affiliated Hospital of Jinan University, No 613 Huangpu Dadao West, Guangzhou, 510630, China

    Xukai Mo & Changzheng Shi

  3. Engineering Research Center of Medical Imaging Artificial Intelligence for Precision Diagnosis and Treatment, No 613 Huangpu Dadao West, Guangzhou, 610630, China

    Xukai Mo & Changzheng Shi

  4. School of Biomedical Engineering, Sun Yat-sen University, No. 135, Xingang Xi Road, Guangzhou, 510275, China

    Heye Zhang

  5. National Heart and Lung Institute, Imperial College London, London, SW7 2AZ, UK

    Guang Yang

  6. Department of Medicine and Therapeutics, Faculty of Medicine, The Chinese University of Hong Kong, 30-32 Ngan Shing St., Sha Tin, Hong Kong, SAR, China

    William Kongtou Hau

Authors
  1. Xin Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xukai Mo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Heye Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guang Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Changzheng Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. William Kongtou Hau
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Changzheng Shi.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Changzheng Shi.

Conflict of interest

The authors report no relationships that could be construed as a conflict of interest.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was obtained.

Ethical approval

Institutional Review Board approved the present study.

Methodology

• retrospective

• observational

• performed at one institution

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, X., Mo, X., Zhang, H. et al. A 2-year investigation of the impact of the computed tomography–derived fractional flow reserve calculated using a deep learning algorithm on routine decision-making for coronary artery disease management. Eur Radiol 31, 7039–7046 (2021). https://doi.org/10.1007/s00330-021-07771-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-021-07771-7

Keywords

Search

Navigation