Automated estimation of image quality for coronary computed tomographic angiography using machine learning

  • Rine Nakanishi
  • Sethuraman Sankaran
  • Leo Grady
  • Jenifer Malpeso
  • Razik Yousfi
  • Kazuhiro Osawa
  • Indre Ceponiene
  • Negin Nazarat
  • Sina Rahmani
  • Kendall Kissel
  • Eranthi Jayawardena
  • Christopher Dailing
  • Christopher Zarins
  • Bon-Kwon Koo
  • James K. Min
  • Charles A. Taylor
  • Matthew J. Budoff
Cardiac

Abstract

Objectives

Our goal was to evaluate the efficacy of a fully automated method for assessing the image quality (IQ) of coronary computed tomography angiography (CCTA).

Methods

The machine learning method was trained using 75 CCTA studies by mapping features (noise, contrast, misregistration scores, and un-interpretability index) to an IQ score based on manual ground truth data. The automated method was validated on a set of 50 CCTA studies and subsequently tested on a new set of 172 CCTA studies against visual IQ scores on a 5-point Likert scale.

Results

The area under the curve in the validation set was 0.96. In the 172 CCTA studies, our method yielded a Cohen’s kappa statistic for the agreement between automated and visual IQ assessment of 0.67 (p < 0.01). In the group where good to excellent (n = 163), fair (n = 6), and poor visual IQ scores (n = 3) were graded, 155, 5, and 2 of the patients received an automated IQ score > 50 %, respectively.

Conclusion

Fully automated assessment of the IQ of CCTA data sets by machine learning was reproducible and provided similar results compared with visual analysis within the limits of inter-operator variability.

Key points

The proposed method enables automated and reproducible image quality assessment.

Machine learning and visual assessments yielded comparable estimates of image quality.

Automated assessment potentially allows for more standardised image quality.

Image quality assessment enables standardization of clinical trial results across different datasets.

Keyword

Computed tomography angiography Coronary vessels Cardiac imaging techniques Machine learning Image enhancement 

Abbreviations

AUC

Area under the curve

CAD

Coronary artery disease

CCTA

Coronary computed tomographic angiography

CNR

Contrast-to-noise ratio

FFR

Fractional flow reserve

ICA

Invasive coronary angiography

IQ

Image quality

ML

Machine learning

Notes

Compliance with ethical standards

Guarantor

The scientific guarantor of this publication is Dr. Matthew J. Budoff.

Conflict of interest

The authors of this manuscript declare relationships with the following companies: Dr. Matthew Budoff receives grant support from GE Healthcare. Dr. Sankaran, Dr. Grady, Mr. Yousfi, Dr. Zarins, and Dr. Taylor are employees of HeartFlow. Dr. Min received modest speakers’ bureau medical advisory board compensation and significant research support from GE Healthcare. All other 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

No complex statistical methods were necessary in the current study.

Informed consent

Written informed consent was obtained from all subjects (patients) in this study.

Ethical approval

Institutional Review Board approval was obtained.

Study subjects or cohorts overlap

Some study subjects have been previously reported in the JAMA and JACC.

Methodology

• This is a retrospective observational study using two previous multicentre studies.

References

  1. 1.
    Budoff MJ, Dowe D, Jollis JG et al (2008) Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease: results from the prospective multicenter ACCURACY (Assessment by Coronary Computed Tomographic Angiography of Individuals Undergoing Invasive Coronary Angiography) trial. J Am Coll Cardiol 52(21):1724–1732CrossRefPubMedGoogle Scholar
  2. 2.
    Achenbach S, Moselewski F, Ropers D et al (2004) Detection of calcified and noncalcified coronary atherosclerotic plaque by contrast-enhanced, submillimeter multidetector spiral computed tomography: a segment-based comparison with intravascular ultrasound. Circulation. 109(1):14–17CrossRefPubMedGoogle Scholar
  3. 3.
    Min JK, Leipsic J, Pencina MJ et al (2012a) Diagnostic accuracy of fractional flow reserve from anatomic CT angiography. JAMA. 308(12):1237–1245CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Douglas PS, Hoffmann U, Patel MR et al (2015) Outcomes of anatomical versus functional testing for coronary artery disease. N Engl J Med. 372(14):1291–1300CrossRefPubMedPubMedCentralGoogle Scholar
  5. 5.
    SCOT-HEART investigators (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):2383–91.Google Scholar
  6. 6.
    Leipsic J, Abbara S, Achenbach S et al (2014) SCCT guidelines for the interpretation and reporting of coronary CT angiography: a report of the Society of Cardiovascular Computed Tomography Guidelines Committee. J Cardiovasc Comput Tomogr. 8(5):342–358CrossRefPubMedGoogle Scholar
  7. 7.
    Naeemi MDRJ, Hollcroft N, Alessio AM, Roychowdhury S (2016) Application of big data analytics for automated estimation of CT image quality. Big Data (Big Data). IEEE International Conference on. IEEE 2016:3422–3431Google Scholar
  8. 8.
    Fronthaler HKK, Bigun J, Fierrez J, Alonso-Fernandez F, Ortega-Garcia J, Gonzalez-Rodriguez J (2008) Fingerprint image-quality estimation and its application to multialgorithm verification. IEEE Transactions on Information Forensics and Security. 3(2):331–338CrossRefGoogle Scholar
  9. 9.
    Marin TKM, Hendrik PP, Wernick MN, Yang Y, Brankov JG (2011) Numerical observer for cardiac motion assessment using machine learning. In Proc. of SPIE. 7966:79660G–796601CrossRefGoogle Scholar
  10. 10.
    Koo BK, Erglis A, Doh JH et al (2011) Diagnosis of ischemia-causing coronary stenoses by noninvasive fractional flow reserve computed from coronary computed tomographic angiograms. Results from the prospective multicenter DISCOVER-FLOW (Diagnosis of Ischemia-Causing Stenoses Obtained Via Noninvasive Fractional Flow Reserve) study. J Am Coll Cardiol. 58(19):1989–1997CrossRefPubMedGoogle Scholar
  11. 11.
    Min JK, Berman DS, Budoff MJ et al (2011) Rationale and design of the DeFACTO (Determination of Fractional Flow Reserve by Anatomic Computed Tomographic AngiOgraphy) study. J Cardiovasc Comput Tomogr. 5(5):301–309CrossRefPubMedGoogle Scholar
  12. 12.
    Leipsic J, Labounty TM, Heilbron B et al (2010) Adaptive statistical iterative reconstruction: assessment of image noise and image quality in coronary CT angiography. AJR Am J Roentgenol. 195(3):649–654CrossRefPubMedGoogle Scholar
  13. 13.
    Min JK, Koo BK, Erglis A et al (2012b) 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(3):191–199CrossRefPubMedGoogle Scholar
  14. 14.
    Abbara S, Blanke P, Maroules CD et al (2016) SCCT guidelines for the performance and acquisition of coronary computed tomographic angiography: A report of the society of Cardiovascular Computed Tomography Guidelines Committee: Endorsed by the North American Society for Cardiovascular Imaging (NASCI). J Cardiovasc Comput Tomogr. 10(6):435–449CrossRefPubMedGoogle Scholar
  15. 15.
    Sun K, Li K, Han R et al (2015) Evaluation of high-pitch dual-source CT angiography for evaluation of coronary and carotid-cerebrovascular arteries. Eur J Radiol. 84(3):398–406CrossRefPubMedGoogle Scholar
  16. 16.
    Zir LM, Miller SW, Dinsmore RE, Gilbert JP, Harthorne JW (1976) Interobserver variability in coronary angiography. Circulation. 53(4):627–632CrossRefPubMedGoogle Scholar
  17. 17.
    Cury RC, Abbara S, Achenbach S et al (2016) CAD-RADS(TM) Coronary Artery Disease - Reporting and Data System. An expert consensus document of the Society of Cardiovascular Computed Tomography (SCCT), the American College of Radiology (ACR) and the North American Society for Cardiovascular Imaging (NASCI). Endorsed by the American College of Cardiology. J Cardiovasc Comput Tomogr. 10(4):269–281CrossRefPubMedGoogle Scholar
  18. 18.
    Hamon M, Biondi-Zoccai GG, Malagutti P et al (2006) Diagnostic performance of multislice spiral computed tomography of coronary arteries as compared with conventional invasive coronary angiography: a meta-analysis. J Am Coll Cardiol. 48(9):1896–1910CrossRefPubMedGoogle Scholar
  19. 19.
    Puchner SB, Liu T, Mayrhofer T et al (2014) High-risk plaque detected on coronary CT angiography predicts acute coronary syndromes independent of significant stenosis in acute chest pain: results from the ROMICAT-II trial. J Am Coll Cardiol. 64(7):684–692CrossRefPubMedPubMedCentralGoogle Scholar

Copyright information

© European Society of Radiology 2018

Authors and Affiliations

  • Rine Nakanishi
    • 1
  • Sethuraman Sankaran
    • 2
  • Leo Grady
    • 2
  • Jenifer Malpeso
    • 1
  • Razik Yousfi
    • 2
  • Kazuhiro Osawa
    • 1
  • Indre Ceponiene
    • 1
  • Negin Nazarat
    • 1
  • Sina Rahmani
    • 1
  • Kendall Kissel
    • 1
  • Eranthi Jayawardena
    • 1
  • Christopher Dailing
    • 1
  • Christopher Zarins
    • 2
  • Bon-Kwon Koo
    • 3
  • James K. Min
    • 4
  • Charles A. Taylor
    • 2
  • Matthew J. Budoff
    • 1
  1. 1.Los Angeles Biomedical Research Institute at Harbor UCLA Medical CenterTorranceUSA
  2. 2.HeartFlow Inc.Redwood CityUSA
  3. 3.Department of MedicineSeoul National University HospitalSeoulSouth Korea
  4. 4.Department of RadiologyWeill Cornell Medical College and the New York Presbyterian HospitalNew YorkUSA

Personalised recommendations