Skip to main content
SpringerLink
Log in

The influence of image quality on diagnostic performance of a machine learning–based fractional flow reserve derived from coronary CT angiography

  • Computed Tomography
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objective

To investigate the effect of image quality of coronary CT angiography (CCTA) on the diagnostic performance of a machine learning–based CT-derived fractional flow reserve (FFRCT).

Methods

This nationwide retrospective study enrolled participants from 10 individual centers across China. FFRCT analysis was performed in 570 vessels in 437 patients. Invasive FFR and FFRCT values ≤ 0.80 were considered ischemia-specific. Four-score subjective assessment based on image quality and objective measurement of vessel enhancement was performed on a per-vessel basis. The effects of body mass index (BMI), sex, heart rate, and coronary calcium score on the diagnostic performance of FFRCT were studied.

Results

Among 570 vessels, 216 were considered ischemia-specific by invasive FFR and 198 by FFRCT. Sensitivity and specificity of FFRCT for detecting lesion-specific ischemia were 0.82 and 0.93, respectively. Area under the curve (AUC) of high-quality images (0.93, n = 159) was found to be superior to low-quality images (0.80, n = 92, p = 0.02). Objective image quality and heart rate were also associated with diagnostic performance of FFRCT, whereas there was no statistical difference in diagnostic performance among different BMI, sex, and calcium score groups (all p > 0.05, Bonferroni correction).

Conclusions

This retrospective multicenter study supported the FFRCT as a noninvasive test in evaluating lesion-specific ischemia. Subjective image quality, vessel enhancement, and heart rate affect the diagnostic performance of FFRCT.

Key Points

• FFR CT can be used to evaluate lesion-specific ischemia.

• Poor image quality negatively affects the diagnostic performance of FFR CT .

• CCTA with ≥ score 3, intracoronary enhancement degree of 300–400 HU, and heart rate below 70 bpm at scanning could be of great benefit to more accurate FFR CT analysis.

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

ACCF:

American College of Cardiology Foundation

AHA:

American Heart Association

ATP:

Adenosine triphosphate

AUC:

Area under the curve

BMI:

Body mass index

bpm:

Beats per minute

CABG:

Coronary artery bypass grafting

CAD:

Stable coronary artery disease

CCTA:

Coronary computed tomography angiography

CFD:

Computational fluid dynamics

CI:

Confidence interval

FFR:

Fractional flow reserve

FFRCT :

Fractional flow reserve derived from coronary computed tomography angiography

ICA:

Invasive coronary angiography

IQR:

Interquartile range

LAD:

Left anterior descending artery

ML:

Machine learning

NPV:

Negative predictive value

PCI:

Percutaneous coronary intervention

PPV:

Positive predictive value

RCA:

Right coronary artery

ROI:

Region of interest

References

  1. Curzen N, Rana O, Nicholas Z et al (2014) Does routine pressure wire assessment influence management strategy at coronary angiography for diagnosis of chest pain?: the RIPCORD study. Circ Cardiovasc Interv 7:248–255

    Article  Google Scholar 

  2. Patel MR, Calhoon JH, Dehmer GJ et al (2017) ACC/AATS/AHA/ASE/ASNC/SCAI/SCCT/STS 2017 Appropriate use criteria for coronary revascularization in patients with stable ischemic heart disease: a report of the American College of Cardiology Appropriate Use Criteria Task Force, American Association for Thoracic Surgery, American Heart Association, American Society of Echocardiography, American Society of Nuclear Cardiology, Society for Cardiovascular Angiography and Interventions, Society of Cardiovascular Computed Tomography, and Society of Thoracic Surgeons. J Nucl Cardiol 24:1759–1792

    Article  Google Scholar 

  3. Windecker S, Kolh P, Alfonso F et al (2014) 2014 ESC/EACTS Guidelines on myocardial revascularization: the task force on myocardial revascularization of the European Society of Cardiology (ESC) and the European Association for Cardio-Thoracic Surgery (EACTS) Developed with the special contribution of the European Association of Percutaneous Cardiovascular Interventions (EAPCI). Eur Heart J 35:2541–2619

  4. Tesche C, De Cecco CN, Albrecht MH et al (2017) Coronary CT angiography-derived fractional flow reserve. Radiology 285:17–33

    Article  Google Scholar 

  5. Nous FMA, Coenen A, Boersma E et al (2019) Comparison of the diagnostic performance of coronary computed tomography angiography-derived fractional flow reserve in patients with versus without diabetes mellitus (from the machine consortium). Am J Cardiol 123:537–543

    Article  Google Scholar 

  6. Norgaard BL, Leipsic J, Gaur S et al (2014) Diagnostic performance of noninvasive fractional flow reserve derived from coronary computed tomography angiography in suspected coronary artery disease: the NXT trial (analysis of coronary blood flow using CT angiography: next steps). J Am Coll Cardiol 63:1145–1155

    Article  Google Scholar 

  7. Coenen A, Lubbers MM, Kurata A et al (2015) Fractional flow reserve computed from noninvasive CT angiography data: diagnostic performance of an on-site clinician-operated computational fluid dynamics algorithm. Radiology 274:674–683

    Article  Google Scholar 

  8. Itu L, Rapaka S, Passerini T et al (2016) A machine-learning approach for computation of fractional flow reserve from coronary computed tomography. J Appl Physiol (1985) 121:42–52

  9. Kruk M, Wardziak Ł, Demkow M et al (2016) Workstation-based calculation of CTA-based FFR for intermediate stenosis. JACC Cardiovasc Imaging 9:690–699

    Article  Google Scholar 

  10. Baumann S, Renker M, Hetjens S et al (2016) Comparison of coronary computed tomography angiography-derived vs invasive fractional flow reserve assessment: meta-analysis with subgroup evaluation of intermediate stenosis. Acad Radiol 23:1402–1411

    Article  Google Scholar 

  11. Tesche C, De Cecco CN, Baumann S et al (2018) Coronary CT angiography-derived fractional flow reserve: machine learning algorithm versus computational fluid dynamics modeling. Radiology 288:64–72

    Article  Google Scholar 

  12. Leipsic J, Yang TH, Thompson A et al (2014) CT angiography (CTA) and diagnostic performance of noninvasive fractional flow reserve: results from the determination of fractional flow reserve by anatomic CTA (DeFACTO) study. AJR Am J Roentgenol 202:989–994

    Article  Google Scholar 

  13. Douglas PS, De Bruyne B, Pontone G et al (2016) 1-year outcomes of FFRCT-guided care in patients with suspected coronary disease: The PLATFORM Study. J Am Coll Cardiol 68:435–445

    Article  Google Scholar 

  14. Douglas PS, Pontone G, Hlatky MA 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 FFR(CT): outcome and resource impacts study. Eur Heart J 36:3359–3367

    Article  CAS  Google Scholar 

  15. Tang CX, Liu CY, Lu MJ et al (2019) CT FFR for ischemia-specific CAD with a new computational fluid dynamics algorithm: a Chinese multicenter study. JACC Cardiovasc Imaging. https://doi.org/10.1016/j.jcmg.2019.06.018

  16. Zhang LJ, Wang Y, Schoepf UJ et al (2016) Image quality, radiation dose, and diagnostic accuracy of prospectively ECG-triggered high-pitch coronary CT angiography at 70 kVp in a clinical setting: comparison with invasive coronary angiography. Eur Radiol 26:797–806

    Article  Google Scholar 

  17. Beitzke D, Berger-Kulemann V, Schöpf V et al (2015) Dual-source cardiac computed tomography angiography (CCTA) in the follow-up of cardiac transplant: comparison of image quality and radiation dose using three different imaging protocols. Eur Radiol 25:2310–2317

    Article  CAS  Google Scholar 

  18. Di Cesare E, Gennarelli A, Di Sibio A et al (2016) 320-row coronary computed tomography angiography (CCTA) with automatic exposure control (AEC): effect of 100 kV versus 120 kV on image quality and dose exposure. Radiol Med 121:618–625

    Article  Google Scholar 

  19. Li Y, Yu M, Li W, Lu Z, Wei M, Zhang J (2018) Third generation dual-source CT enables accurate diagnosis of coronary restenosis in all size stents with low radiation dose and preserved image quality. Eur Radiol 28:2647–2654

    Article  Google Scholar 

  20. Van Cauteren T, Van Gompel G, Tanaka K et al (2017) The impact of combining a low-tube voltage acquisition with iterative reconstruction on total iodine dose in coronary CT angiography. Biomed Res Int 2017:2476171

    PubMed  PubMed Central  Google Scholar 

  21. Fei X, Du X, Yang Q et al (2008) 64-MDCT coronary angiography: phantom study of effects of vascular attenuation on detection of coronary stenosis. AJR Am J Roentgenol 191:43–49

    Article  Google Scholar 

  22. Zhang LJ, Wu SY, Wang J et al (2010) Diagnostic accuracy of dual-source CT coronary angiography: the effect of average heart rate, heart rate variability, and calcium score in a clinical perspective. Acta Radiol 51:727–740

    Article  Google Scholar 

  23. Chian TC, Nassir NM, Ibrahim MI, Yusof AK, Sabarudin A (2017) Quantitative assessment on coronary computed tomography angiography (CCTA) image quality: comparisons between genders and different tube voltage settings. Quant Imaging Med Surg 7:48–58

    Article  Google Scholar 

  24. Agatston A, Janowitz WR, Hildner FJ, Zusmer NR, Viamonte M Jr, Detrano R (1990) Quantification of coronary artery calcium using ultrafast computed tomography. J Am Coll Cardiol 15:827–832

    Article  CAS  Google Scholar 

  25. Greenland P, Bonow RO, Brundage BH et al (2007) ACCF/AHA 2007 clinical expert consensus document on coronary artery calcium scoring by computed tomography in global cardiovascular risk assessment and in evaluation of patients with chest pain: a report of the American College of Cardiology Foundation Clinical Expert Consensus Task Force (ACCF/AHA Writing Committee to Update the 2000 Expert Consensus Document on Electron Beam Computed Tomography) developed in collaboration with the Society of Atherosclerosis Imaging and Prevention and the Society of Cardiovascular Computed Tomography. J Am Coll Cardiol 49:378–402

    Article  Google Scholar 

  26. Solecki M, Kruk M, Demkow M et al (2017) What is the optimal anatomic location for coronary artery pressure measurement at CT-derived FFR? J Cardiovasc Comput Tomogr 11:397–403

    Article  Google Scholar 

  27. Escaned J, Cortés J, Flores A et al (2003) Importance of diastolic fractional flow reserve and dobutamine challenge in physiologic assessment of myocardial bridging. J Am Coll Cardiol 42:226–233

    Article  Google Scholar 

  28. Collet C, Miyazaki Y, Ryan N et al (2018) Fractional flow reserve derived from computed tomographic angiography in patients with multivessel CAD. J Am Coll Cardiol 71:2756–2769

    Article  Google Scholar 

  29. Pontone G, Baggiano A, Andreini D et al (2019) Dynamic stress computed tomography perfusion with a whole-heart coverage scanner in addition to coronary computed tomography angiography and fractional flow reserve computed tomography derived. JACC Cardiovasc Imaging. https://doi.org/10.1016/j.jcmg.2019.02.015

  30. De Geer J, Coenen A, Kim YH et al (2019) Effect of tube voltage on diagnostic performance of fractional flow reserve derived from coronary CT angiography with machine learning: results from the MACHINE registry. AJR Am J Roentgenol 30:1–7

    Google Scholar 

  31. Meyer M, Haubenreisser H, Schoepf UJ et al (2014) Closing in on the k edge: coronary CT angiography at 100, 80, and 70 kV-initial comparison of a second-versus a third-generation dual-source CT system. Radiology 273:373–382

    Article  Google Scholar 

  32. Qi L, Wu SY, Meinel FG et al (2016) Prospectively ECG-triggered high-pitch 80 kVp coronary computed tomography angiography with 30 mL of 270 mg I/mL contrast material and iterative reconstruction. Acta Radiol 57:287–294

    Article  Google Scholar 

  33. Min JK, Koo BK, Erglis A et al (2012) Effect of image quality on diagnostic accuracy of noninvasive fractional flow reserve: results from the prospective multicenter international DISCOVER-FLOW study. J Cardiovasc Comput Tomogr 6:191–199

    Article  Google Scholar 

  34. Dewey M, Vavere AL, Arbab-Zadeh A et al (2010) Patient characteristics as predictors of image quality and diagnostic accuracy of MDCT compared with conventional coronary angiography for detecting coronary artery stenoses: CORE-64 Multicenter International Trial. AJR Am J Roentgenol 194:93–102

    Article  Google Scholar 

  35. Nozue T, Takamura T, Fukui K, Hibi K, Kishi S, Michishita I (2019) Assessment of factors associated with measurability of fractional flow reserve derived from coronary computed tomography angiography in type 2 diabetic patients with intermediate coronary artery stenosis. Int J Cardiovasc Imaging 35:359–365

    Article  Google Scholar 

  36. Nørgaard BL, Gaur S, Leipsic J et al (2015) Influence of coronary calcification on the diagnostic performance of CT angiography derived FFR in coronary artery disease: a substudy of the NXT trial. JACC Cardiovasc Imaging 8:1045–1055

    Article  Google Scholar 

  37. Kawaji T, Shiomi H, Morishita H et al (2017) Feasibility and diagnostic performance of fractional flow reserve measurement derived from coronary computed tomography angiography in real clinical practice. Int J Cardiovasc Imaging 33:271–281

    Article  Google Scholar 

Download references

Acknowledgments

We thank our colleagues from multi-centers for data support, Mengjie Lu from Jinling Hospital for statistical advice, Changsheng Zhou from Jinling Hospital for technical assistance. The work was supported by The National Key Research and Development Program of China (2017YFC0113400 for L.J.Z.).

Funding

The authors state that this work has not received any funding.

Author information

Author notes

  1. Peng Peng Xu and Jian Hua Li contributed equally to this work.

Authors and Affiliations

  1. Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China

    Peng Peng Xu, Fan Zhou, Meng Di Jiang, Chang Sheng Zhou, Meng Jie Lu, Chun Xiang Tang, Xiao Lei Zhang, Liu Yang, Guang Ming Lu, Qian Qian Ni & Long Jiang Zhang

  2. Department of Cardiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, Jiangsu, China

    Jian Hua Li

  3. Laboratory of Image Science and Technology, School of Computer Science and Engineering, Southeast University, Nanjing, 210096, Jiangsu, China

    Yuan Xiu Zhang

  4. Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China

    Yi Ning Wang & Yan Yi

  5. Institute of Diagnostic and Interventional Radiology and Department of Cardiology, Shanghai Jiao Tong University Affiliated Sixth People’s Hospital, Shanghai, 200233, China

    Jia Yin Zhang & Meng Meng Yu

  6. Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, 110001, China

    Yang Hou

  7. Department of Radiology, Xijing Hospital, Fourth Military Medical University, Xi’an, Shaanxi, China

    Min Wen Zheng

  8. Department of Radiology, Jiangsu Taizhou People’s Hospital, Taizhou, 225300, China

    Bo Zhang

  9. Department of Cardiology, Nanjing First Hospital, Nanjing Medical University, Nanjing, 210006, Jiangsu, China

    Dai Min Zhang

  10. Department of Radiology, Beijing Anzhen Hospital, Capital Medical University, Beijing, 10029, China

    Lei Xu

  11. Sir Run Run Shaw Hospital, Zhejiang University, Zhejiang, 310016, Hangzhou, China

    Xiu Hua Hu

  12. Department of Radiology, Guangdong Provincial People’s Hospital, Guangzhou, 510030, China

    Hui Liu

Authors
  1. Peng Peng Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jian Hua Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fan Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Meng Di Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Chang Sheng Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Meng Jie Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Chun Xiang Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Xiao Lei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Liu Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Yuan Xiu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Yi Ning Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Jia Yin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Meng Meng Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Yang Hou
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Min Wen Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Bo Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Dai Min Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  18. Yan Yi
    View author publications

    You can also search for this author in PubMed Google Scholar

  19. Lei Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  20. Xiu Hua Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  21. Hui Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  22. Guang Ming Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  23. Qian Qian Ni
    View author publications

    You can also search for this author in PubMed Google Scholar

  24. Long Jiang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Qian Qian Ni or Long Jiang Zhang.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Long Jiang Zhang.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

Meng Jie Lu kindly provided statistical advice for this manuscript.

One of the authors has significant statistical expertise.

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• Retrospective

• Cross-sectional study

• Multicenter study

Additional information

Publisher’s note

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

Electronic supplementary material

ESM 1

(DOCX 201 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, P.P., Li, J.H., Zhou, F. et al. The influence of image quality on diagnostic performance of a machine learning–based fractional flow reserve derived from coronary CT angiography. Eur Radiol 30, 2525–2534 (2020). https://doi.org/10.1007/s00330-019-06571-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-019-06571-4

Keywords

Search

Navigation