Skip to main content

Advertisement

SpringerLink
Log in

“Global” cardiac atherosclerotic burden assessed by artificial intelligence-based versus manual segmentation in 18F-sodium fluoride PET/CT scans: Head-to-head comparison

  • Original Article
  • Published:
Journal of Nuclear Cardiology Aims and scope

Abstract

Background

Artificial intelligence (AI) is known to provide effective means to accelerate and facilitate clinical and research processes. So in this study it was aimed to compare a AI-based method for cardiac segmentation in positron emission tomography/computed tomography (PET/CT) scans with manual segmentation to assess global cardiac atherosclerosis burden.

Methods

A trained convolutional neural network (CNN) was used for cardiac segmentation in 18F-sodium fluoride PET/CT scans of 29 healthy volunteers and 20 angina pectoris patients and compared with manual segmentation. Parameters for segmented volume (Vol) and mean, maximal, and total standardized uptake values (SUVmean, SUVmax, SUVtotal) were analyzed by Bland-Altman Limits of Agreement. Repeatability with AI-based assessment of the same scans is 100%. Repeatability (same conditions, same operator) and reproducibility (same conditions, two different operators) of manual segmentation was examined by re-segmentation in 25 randomly selected scans.

Results

Mean (± SD) values with manual vs. CNN-based segmentation were Vol 617.65 ± 154.99 mL vs 625.26 ± 153.55 mL (P = .21), SUVmean 0.69 ± 0.15 vs 0.69 ± 0.15 (P = .26), SUVmax 2.68 ± 0.86 vs 2.77 ± 1.05 (P = .34), and SUVtotal 425.51 ± 138.93 vs 427.91 ± 132.68 (P = .62). Limits of agreement were − 89.42 to 74.2, − 0.02 to 0.02, − 1.52 to 1.32, and − 68.02 to 63.21, respectively. Manual segmentation lasted typically 30 minutes vs about one minute with the CNN-based approach. The maximal deviation at manual re-segmentation was for the four parameters 0% to 0.5% with the same and 0% to 1% with different operators.

Conclusion

The CNN-based method was faster and provided values for Vol, SUVmean, SUVmax, and SUVtotal comparable to the manually obtained ones. This AI-based segmentation approach appears to offer a more reproducible and much faster substitute for slow and cumbersome manual segmentation of the heart.

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

Figure 1
Figure 2
Figure 3

Similar content being viewed by others

Abbreviations

AI:

Artificial intelligence

CNN:

Convolutional neural network

CT:

Computed tomography

NaF:

18F- sodium fluoride

PET:

Positron emission tomography

ROI:

Region of interest

SUV:

Standardized uptake value

VOI:

Volume of interest

References

  1. Arbab-Zadeh A, Fuster V. The myth of the “vulnerable plaque” transitioning from a focus on individual lesions to atherosclerotic disease burden for coronary artery disease risk assessment. J Am Coll Cardiol 2015;65:846-55.

    Article  Google Scholar 

  2. Irkle A, Vesey AT, Lewis DY, Skepper JN, Bird JL, Dweck MR, et al. Identifying active vascular microcalcification by 18 F-sodium fluoride positron emission tomography. Nat Commun 2015;6:1-11.

    Article  Google Scholar 

  3. Tarkin JM, Dweck MR, Evans NR, Takx RA, Brown AJ, Tawakol A, et al. Imaging atherosclerosis. Circ Res 2016;118:750-69.

    Article  CAS  Google Scholar 

  4. McKenney-Drake ML, Moghbel MC, Paydary K, Alloosh M, Houshmand S, Moe S, et al. 18 F-NaF and 18 F-FDG as molecular probes in the evaluation of atherosclerosis. Eur J Nucl Med Mol Imaging 2018;45:2190-2200.

    Article  Google Scholar 

  5. Belal SL, Sadik M, Kaboteh R, Enqvist O, Ulén J, Poulsen MH, et al. Deep learning for segmentation of 49 selected bones in CT scans: First step in automated PET/CT-based 3D quantification of skeletal metastases. Eur J Radiol 2019;113:89-95.

    Article  Google Scholar 

  6. Dou Q, Yu L, Chen H, Jin Y, Yang X, Qin J, et al. 3D deeply supervised network for automated segmentation of volumetric medical images. Med Image Anal 2017;41:40-54.

    Article  Google Scholar 

  7. Mortensen MA, Borrelli P, Poulsen MH, Gerke O, Enqvist O, Ulén J. et al. Artificial intelligence-based versus manual assessment of prostate cancer in the prostate gland: A method comparison study. Clin Physiol Funct Imaging 2019;39:399-406.

    Article  CAS  Google Scholar 

  8. Polymeri E, Sadik M, Kaboteh R, Borrelli P, Enqvist O, Ulén J, et al. Deep learning-based quantification of PET/CT prostate gland uptake: Association with overall survival. Clin Physiol Funct Imaging 2020;40:106-13.

    Article  CAS  Google Scholar 

  9. Blomberg BA, de Jong PA, Thomassen A, Lam MG, Vach W, Olsen MH, et al. Thoracic aorta calcification but not inflammation is associated with increased cardiovascular disease risk: Results of the CAMONA study. Eur J Nucl Med Mol Imaging 2017;44:249-58.

    Article  Google Scholar 

  10. Blomberg BA, Thomassen A, Takx RA, Vilstrup MH, Hess S, Nielsen AL, et al. Delayed sodium 18 F-fluoride PET/CT imaging does not improve quantification of vascular calcification metabolism: Results from the CAMONA study. J Nucl Cardiol 2014;21:293-304.

    Article  Google Scholar 

  11. Trägårdh E, Borrelli P, Kaboteh R, Gillberg T, Ulén J, Enqvist O, et al. RECOMIA—a cloud-based platform for artificial intelligence research in nuclear medicine and radiology. EJNMMI Phys 2020;7:1-12.

    Article  Google Scholar 

  12. Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. International conference on medical image computing and computer-assisted intervention; 2016. pp. 424-32.

  13. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:abs/14126980 2014.

  14. Carkeet A. Exact parametric confidence intervals for Bland-Altman limits of agreement. Optom Vis Sci 2015;92:e71-e80.

    Article  Google Scholar 

  15. Gerke O. Reporting standards for a Bland-Altman agreement analysis: A review of methodological reviews. Diagnostics 2020;10:334.

    Article  Google Scholar 

  16. Zijdenbos AP, Dawant BM, Margolin RA, Palmer AC. Morphometric analysis of white matter lesions in MR images: Method and validation. IEEE Trans Med Imaging 1994;13:716-24.

    Article  CAS  Google Scholar 

  17. Miller RJH, Slomka PJ. Artificial intelligence-based attenuation correction; closer to clinical reality? J Nucl Cardiol 2020. https://doi.org/10.1007/s12350-021-02724-5.

    Article  PubMed  PubMed Central  Google Scholar 

  18. Zheng C, Sun BC, Wu Y-L, Ferencik M, Lee M-S, Redberg RF, et al. Automated abstraction of myocardial perfusion imaging reports using natural language processing. J Nucl Cardiol 2020. https://doi.org/10.1007/s12350-020-02401-z.

    Article  PubMed  Google Scholar 

  19. Sharedalal P, Singh A, Shah N, Jain D. Automated abstraction of myocardial perfusion imaging reports using natural language processing. J Nucl Cardiol 2021. https://doi.org/10.1007/s12350-020-02507-4.

    Article  PubMed  Google Scholar 

  20. Garcia EV, Klein JL, Moncayo V, Cooke CD, Del’Aune C, Folks R, et al. Diagnostic performance of an artificial intelligence-driven cardiac-structured reporting system for myocardial perfusion SPECT imaging. J Nucl Cardiol 2020;27:1652-64. https://doi.org/10.1007/s12350-018-1432-3.

    Article  PubMed  Google Scholar 

  21. Haro Alonso D, Wernick MN, Yang Y, Germano G, Berman DS, Slomka P. Prediction of cardiac death after adenosine myocardial perfusion SPECT based on machine learning. J Nucl Cardiol 2019;26:1746-54. https://doi.org/10.1007/s12350-018-1250-7.

    Article  PubMed  Google Scholar 

  22. Nappi C, Cuocolo A. The machine learning approach: Artificial intelligence is coming to support critical clinical thinking. J Nucl Cardiol 2020;27:156-8. https://doi.org/10.1007/s12350-018-1344-2.

    Article  PubMed  Google Scholar 

  23. Piri R, Edenbrandt L, Larsson M, Enqvist O, Nøddeskou-Fink AH, Gerke O, et al. Aortic wall segmentation in 18 F-sodium fluoride PET/CT scans: Head-to-head comparison of artificial intelligence-based versus manual segmentation. J Nucl Cardiol 2021. https://doi.org/10.1007/s12350-021-02649-z.

    Article  PubMed  Google Scholar 

  24. Lindgren Belal S, Sadik M, Kaboteh R, Enqvist O, Ulén J, Poulsen MH, et al. Deep learning for segmentation of 49 selected bones in CT scans: First step in automated PET/CT-based 3D quantification of skeletal metastases. Eur J Radiol 2019;113:89-95. https://doi.org/10.1016/j.ejrad.2019.01.028.

    Article  PubMed  Google Scholar 

  25. Høilund-Carlsen PF, Edenbrandt L, Alavi A. Global disease score (GDS) is the name of the game! Eur J Nucl Med Mol Imaging 2019;46:1768-72. https://doi.org/10.1007/s00259-019-04383-8.

    Article  PubMed  PubMed Central  Google Scholar 

  26. Høilund-Carlsen PF, Sturek M, Alavi A, Gerke O. Atherosclerosis imaging with 18 F-sodium fluoride PET: State-of-the-art review. Eur J Nucl Med Mol Imaging 2020;47:1538-51.

    Article  Google Scholar 

  27. Zuluaga MA, Cardoso MJ, Modat M, Ourselin S. Multi-atlas propagation whole heart segmentation from MRI and CTA using a local normalised correlation coefficient criterion. International Conference on Functional Imaging and Modeling of the Heart; 2013. pp. 174-81.

  28. Diederichsen SZ, Grønhøj MH, Mickley H, Gerke O, Steffensen FH, Lambrechtsen J, et al. CT-detected growth of coronary artery calcification in asymptomatic middle-aged subjects and association with 15 biomarkers. JACC Cardiovasc Imaging 2017;10:858-66. https://doi.org/10.1016/j.jcmg.2017.05.010.

    Article  PubMed  Google Scholar 

  29. McClelland RL, Chung H, Detrano R, Post W, Kronmal RA. Distribution of coronary artery calcium by race, gender, and age. Circulation 2006;113:30-7. https://doi.org/10.1161/CIRCULATIONAHA.105.580696.

    Article  PubMed  Google Scholar 

  30. Schmermund A, Möhlenkamp S, Berenbein S, Pump H, Moebus S, Roggenbuck U, et al. Population-based assessment of subclinical coronary atherosclerosis using electron-beam computed tomography. Atherosclerosis 2006;185:177-82. https://doi.org/10.1016/j.atherosclerosis.2005.06.003.

    Article  CAS  PubMed  Google Scholar 

  31. Bonte FJ, Parkey RW, Graham KD, Moore J, Stokely EM. A new method for radionuclide imaging of myocardial infarcts. Radiology 1974;110:473-4. https://doi.org/10.1148/110.2.473.

    Article  CAS  PubMed  Google Scholar 

  32. Morbelli S, Fiz F, Piccardo A, Picori L, Massollo M, Pestarino E, et al. Divergent determinants of 18 F-NaF uptake and visible calcium deposition in large arteries: Relationship with Framingham risk score. Int J Cardiovasc Imaging 2014;30:439-47.

    Article  Google Scholar 

  33. Raynor W, Houshmand S, Gholami S, Emamzadehfard S, Rajapakse CS, Blomberg BA, et al. Evolving role of molecular imaging with 18 F-sodium fluoride PET as a biomarker for calcium metabolism. Curr Osteoporos Rep 2016;14:115-25.

    Article  Google Scholar 

  34. Sorci O, Batzdorf AS, Mayer M, Rhodes S, Peng M, Jankelovits AR, et al. 18 F-sodium fluoride PET/CT provides prognostic clarity compared to calcium and Framingham risk scoring when addressing whole-heart arterial calcification. Eur J Nucl Med Mol Imaging 2019;47:1-10.

    Google Scholar 

  35. Hanson MA, Fareed MT, Argenio SL, Agunwamba AO, Hanson TR. Coronary artery disease. Prim Care 2013;40:1-16.

    Article  Google Scholar 

Download references

Funding

The study was partly funded through a PhD scholarship to Reza Piri by the University of Southern Denmark, Odense, Denmark.

Author information

Authors and Affiliations

  1. Department of Nuclear Medicine, Odense University Hospital, 5000, Odense C, Denmark

    Reza Piri MD, Sofie Skovrup BSc, Oke Gerke MSc, PhD & Poul Flemming Høilund-Carlsen MD, DMSc

  2. Department of Clinical Research, University of Southern Denmark, Odense, Denmark

    Reza Piri MD, Oke Gerke MSc, PhD & Poul Flemming Høilund-Carlsen MD, DMSc

  3. Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden

    Lars Edenbrandt MD, DMSc

  4. Department of Clinical Physiology, Sahlgrenska University Hospital, Region Västra Götaland, Gothenburg, Sweden

    Lars Edenbrandt MD, DMSc

  5. Eigenvision AB, Malmö, Sweden

    Måns Larsson MSc, PhD & Olof Enqvist MSc, PhD

  6. Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden

    Olof Enqvist MSc, PhD

  7. Department of Cardiology, Herlev and Gentofte Hospital, Copenhagen, Denmark

    Kasper Karmark Iversen MD, DMSc

  8. Department of Emergency Medicine, Herlev and Gentofte Hospital, Copenhagen, Denmark

    Kasper Karmark Iversen MD, DMSc

  9. Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, PA, USA

    Babak Saboury MD, MPH, DABR, DABNM & Abass Alavi MD, MD(Hon), PhD(Hon), DSc(Hon)

  10. Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, Baltimore, MD, USA

    Babak Saboury MD, MPH, DABR, DABNM

  11. Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health (NIH), Bethesda, MD, USA

    Babak Saboury MD, MPH, DABR, DABNM

Authors
  1. Reza Piri MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lars Edenbrandt MD, DMSc
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Måns Larsson MSc, PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Olof Enqvist MSc, PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sofie Skovrup BSc
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kasper Karmark Iversen MD, DMSc
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Babak Saboury MD, MPH, DABR, DABNM
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Abass Alavi MD, MD(Hon), PhD(Hon), DSc(Hon)
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Oke Gerke MSc, PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Poul Flemming Høilund-Carlsen MD, DMSc
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Reza Piri MD.

Ethics declarations

Disclosures

None declared.

Additional information

Publisher's Note

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

The authors of this article have provided a PowerPoint file, available for download at SpringerLink, which summarizes the contents of the paper and is free for re-use at meetings and presentations. Search for the article DOI on SpringerLink.com.

The authors have also provided an audio summary of the article, which is available to download as ESM, or to listen to via the JNC/ASNC Podcast.

Supplementary Information

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Piri, R., Edenbrandt, L., Larsson, M. et al. “Global” cardiac atherosclerotic burden assessed by artificial intelligence-based versus manual segmentation in 18F-sodium fluoride PET/CT scans: Head-to-head comparison. J. Nucl. Cardiol. 29, 2531–2539 (2022). https://doi.org/10.1007/s12350-021-02758-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12350-021-02758-9

Keywords

Search

Navigation