Skip to main content

Advertisement

SpringerLink
Log in

Human vs. machine vs. core lab for the assessment of coronary atherosclerosis with lumen and vessel contour segmentation with intravascular ultrasound

  • Original Paper
  • Published:
The International Journal of Cardiovascular Imaging Aims and scope Submit manuscript

Abstract

A machine learning (ML) algorithm for automatic segmentation of intravascular ultrasound was previously validated. It has the potential to improve efficiency, accuracy and precision of coronary vessel segmentation compared to manual segmentation by interventional cardiology experts. The aim of this study is to compare the performance of human readers to the machine and against the readings from a Core Laboratory. This is a post-hoc, cross-sectional analysis of the IBIS-4 study. Forty frames were randomly selected and analyzed by 10 readers of varying expertise two separate times, 1 week apart. Their measurements of lumen, vessel, plaque areas, and plaque burden were performed in an offline software. Among humans, the intra-observer variability was not statistically significant. For the total 80 frames, inter-observer variability between human readers, the ML algorithm and Core Laboratory for lumen area, vessel area, plaque area and plaque burden were not statistically different. For lumen area, however, relative differences between the human readers and the Core Lab ranged from 0.26 to 12.61%. For vessel area, they ranged from 1.25 to 9.54%. Efficiency between the ML algorithm and the readers differed notably. Humans spent 47 min on average to complete the analyses, while the ML algorithm took on average less than 1 min. The overall lumen, vessel and plaque means analyzed by humans and the proposed ML algorithm are similar to those of the Core Lab. Machines, however, are more time efficient. It is warranted to consider use of the ML algorithm in clinical practice.

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
Fig. 3

Similar content being viewed by others

Abbreviations

CAD:

Coronary artery disease

CL:

Core Laboratory

GT:

Ground truth

IVUS:

Intravascular ultrasound

MACE:

Major adverse cardiac event

MFCNN:

Multi-frame convolutional neural network

MLA:

Minimum Lumen Area

ML:

Machine learning

PAV:

Percent atheroma volume

PCI:

Percutaneous coronary intervention

References

  1. Kotecha T, Rakhit RD (2016) Acute coronary syndromes. Clin Med (Lond) 16:s43–s48

    Article  PubMed  Google Scholar 

  2. Garcia-Garcia HM, Costa MA, Serruys PW (2010) Imaging of coronary atherosclerosis: intravascular ultrasound. Eur Heart J 31:2456–2469

    Article  PubMed  Google Scholar 

  3. Neumann F-J, Sousa-Uva M, Ahlsson A, Alfonso F, Banning AP, Benedetto U, Byrne RA, Collet J-P, Falk V, Head SJ, Jüni P, Kastrati A, Koller A, Kristensen SD, Niebauer J, Richter DJ, Seferović PM, Sibbing D, Stefanini GG, Windecker S, Yadav R, Zembala MO, ESC Scientific Document Group (2018) ESC/EACTS guidelines on myocardial revascularization. Eur Heart J 2019(40):87–165

    Google Scholar 

  4. Steinvil A, Zhang Y-J, Lee SY, Pang S, Waksman R, Chen S-L, Garcia-Garcia HM (2016) Intravascular ultrasound-guided drug-eluting stent implantation: an updated meta-analysis of randomized control trials and observational studies. Int J Cardiol 216:133–139

    Article  PubMed  Google Scholar 

  5. Mentias A, Sarrazin MV, Saad M, Panaich S, Kapadia S, Horwitz PA, Girotra S (2020) Long-term outcomes of coronary stenting with and without use of intravascular ultrasound. JACC Cardiovasc Interv 13:1880–1890

    Article  PubMed  PubMed Central  Google Scholar 

  6. Ziemer PGP, Bulant CA, Orlando JI, Maso Talou GD, Álvarez LAM, Guedes Bezerra C, Lemos PA, García-García HM, Blanco PJ (2020) Automated lumen segmentation using multi-frame convolutional neural networks in intravascular ultrasound datasets. Eur Heart J Digit Health 1:75–82

    Article  PubMed  PubMed Central  Google Scholar 

  7. Katouzian A, Angelini ED, Carlier SG, Suri JS, Navab N, Laine AF (2012) A state-of-the-art review on segmentation algorithms in intravascular ultrasound (IVUS) images. IEEE Trans Inf Technol Biomed 16:823–834

    Article  PubMed  Google Scholar 

  8. Cho H, Kang S-J, Min H-S, Lee J-G, Kim W-J, Kang SH, Kang D-Y, Lee PH, Ahn J-M, Park D-W, Lee S-W, Kim Y-H, Lee CW, Park S-W, Park S-J (2021) Intravascular ultrasound-based deep learning for plaque characterization in coronary artery disease. Atherosclerosis 324:69–75

    Article  CAS  PubMed  Google Scholar 

  9. Lee J-G, Ko J, Hae H, Kang S-J, Kang D-Y, Lee PH, Ahn J-M, Park D-W, Lee S-W, Kim Y-H, Lee CW, Park S-W, Park S-J (2020) Intravascular ultrasound-based machine learning for predicting fractional flow reserve in intermediate coronary artery lesions. Atherosclerosis 292:171–177

    Article  CAS  PubMed  Google Scholar 

  10. Li K, Tong J, Zhu X, Xia S (2021) Automatic lumen border detection in IVUS images using deep learning model and handcrafted features. Ultrason Imaging 43:59–73

    Article  PubMed  Google Scholar 

  11. Räber L, Taniwaki M, Zaugg S, Kelbæk H, Roffi M, Holmvang L, Noble S, Pedrazzini G, Moschovitis A, Lüscher TF, Matter CM, Serruys PW, Jüni P, Garcia-Garcia HM, Windecker S, for the IBIS 4 (Integrated Biomarkers and Imaging Study-4) Trial Investigators (NCT00962416) (2015) Effect of high-intensity statin therapy on atherosclerosis in non-infarct-related coronary arteries (IBIS-4): a serial intravascular ultrasonography study. Eur Heart J 36:490–500

  12. Blanco PJ, Ziemer PGP, Bulant CA, Ueki Y, Bass R, Räber L, Lemos PA, García-García HM (2021) Fully automated lumen and vessel contour segmentation in intravascular ultrasound datasets. Med Image Anal 75:102262

    Article  PubMed  Google Scholar 

  13. Maso Talou GD, Larrabide I, Blanco PJ, Bezerra CG, Lemos PA, Feijoo RA (2015) Improving cardiac phase extraction in IVUS studies by integration of gating methods. IEEE Trans Biomed Eng 62:2867–2877

    Article  PubMed  Google Scholar 

  14. Jensen LO, Thayssen P, Pedersen KE, Stender S, Haghfelt T (2004) Low variation and high reproducibility in plaque volume with intravascular ultrasound. Int J Cardiol 97:463–469

    Article  PubMed  Google Scholar 

  15. Blessing E, Hausmann D, Sturm M, Wolpers H-G, Amende I, Mügge A (1999) Intravascular ultrasound and stent implantation: intraobserver and interobserver variability. Am Heart J 137:368–371

    Article  CAS  PubMed  Google Scholar 

  16. Nicholls SJ, Hsu A, Wolski K, Hu B, Bayturan O, Lavoie A, Uno K, Tuzcu EM, Nissen SE (2010) Intravascular ultrasound-derived measures of coronary atherosclerotic plaque burden and clinical outcome. J Am Coll Cardiol 55:2399–2407

    Article  PubMed  Google Scholar 

  17. Nissen SE, Tuzcu EM, Schoenhagen P, Brown BG, Ganz P, Vogel RA, Crowe T, Howard G, Cooper CJ, Brodie B, Grines CL, DeMaria AN, REVERSAL Investigators (2004) Effect of intensive compared with moderate lipid-lowering therapy on progression of coronary atherosclerosis: a randomized controlled trial. JAMA 291:1071–1080

Download references

Funding

The authors declare that no funds, grants, or other support were received in relation to the preparation of this manuscript.

Author information

Authors and Affiliations

  1. School of Medicine, Georgetown University, Washington, DC, USA

    Ronald D. Bass & JooHee Choi

  2. Interventional Cardiology, MedStar Washington Hospital Center, Washington, DC, USA

    Hector M. Garcia-Garcia, Kayode K. Kuku, Yirga A. Kahsay, Solomon Beyene, Gebremedhin Melaku & Estefanía Fernández-Peregrina

  3. Hospital Universitari i Politecnic La Fe, Valencia, Spain

    Jorge Sanz-Sánchez

  4. Centro de Investigación Biomedica en Red (CIBERCV), Madrid, Spain

    Jorge Sanz-Sánchez

  5. National Laboratory for Scientific Computing, Petrópolis, Brazil

    Paulo G. P. Ziemer & Pablo J. Blanco

  6. National Scientific and Technical Research Council, Tandil, Argentina

    Carlos A. Bulant

  7. Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland

    Tatsuhiko Otsuka & Lorenz Räber

  8. Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK

    Emrah Erdogan & Christos V. Bourantas

  9. Interventional Cardiology, Hospital Universitario Clínico San Carlos, Madrid, Spain

    Nieves Gonzalo

  10. Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University of London, London, UK

    Christos V. Bourantas

  11. Division of Interventional Cardiology of MedStar Cardiovascular Research Network at MedStar Washington Hospital Center, 110 Irving Street, Suite 4B-1, Washington, DC, 20010, USA

    Hector M. Garcia-Garcia

Authors
  1. Ronald D. Bass
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hector M. Garcia-Garcia
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jorge Sanz-Sánchez
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Paulo G. P. Ziemer
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Carlos A. Bulant
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kayode K. Kuku
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Yirga A. Kahsay
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Solomon Beyene
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Gebremedhin Melaku
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Tatsuhiko Otsuka
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. JooHee Choi
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Estefanía Fernández-Peregrina
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Emrah Erdogan
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Nieves Gonzalo
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Christos V. Bourantas
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Pablo J. Blanco
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Lorenz Räber
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

RDB, HMG and PJB participated in conception, design, statistical analysis, manuscript drafting and revision. LR and TO collected data and contributed to design, revision and final approval. JS and JC helped to draft and critically revise the manuscript. PGPZ, CAB, KK, YAK, SB, GM, EFP, EE, NG, and CVB aided in analysis and critically revised the manuscript. All authors provided final approval.

Corresponding author

Correspondence to Hector M. Garcia-Garcia.

Ethics declarations

Conflict of interest

HM. Garcia-Garcia reports the following Institutional grant support: Biotronik, Boston Scientific, Medtronic, Abbott, Neovasc, Shockwave, Phillips and Corflow; E. Fernández-Peregrina reports having received a research grant from the Spanish Society of Cardiology. Lorenz Räber reports institutional grant support: Abbott, Biotronik, Boston Scientific, Sanofi, Regeneron, Infraredx and consultation fees by Abbott, Amgen, AstraZeneca, Occlutec, Medtronic, Sanofi, Vifor.

Ethical approval

The study protocol conforms to ethical guidelines and has been priorly approved by the Institutional Review Board.

Consent to participate

Informed consent was obtained from each patient included in the study.

Consent to publish

The participants have consented to the submission of this study to the journal.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 4050 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bass, R.D., Garcia-Garcia, H.M., Sanz-Sánchez, J. et al. Human vs. machine vs. core lab for the assessment of coronary atherosclerosis with lumen and vessel contour segmentation with intravascular ultrasound. Int J Cardiovasc Imaging 38, 1431–1439 (2022). https://doi.org/10.1007/s10554-022-02563-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10554-022-02563-6

Keywords

Search

Navigation