Skip to main content

Advertisement

SpringerLink
Log in

Diagnostic performance of deep learning algorithm for analysis of computed tomography myocardial perfusion

  • Original Article
  • Published:
European Journal of Nuclear Medicine and Molecular Imaging Aims and scope Submit manuscript

Abstract

Purpose

To evaluate the diagnostic accuracy of a deep learning (DL) algorithm predicting hemodynamically significant coronary artery disease (CAD) by using a rest dataset of myocardial computed tomography perfusion (CTP) as compared to invasive evaluation.

Methods

One hundred and twelve consecutive symptomatic patients scheduled for clinically indicated invasive coronary angiography (ICA) underwent CCTA plus static stress CTP and ICA with invasive fractional flow reserve (FFR) for stenoses ranging between 30 and 80%. Subsequently, a DL algorithm for the prediction of significant CAD by using the rest dataset (CTP-DLrest) and stress dataset (CTP-DLstress) was developed. The diagnostic accuracy for identification of significant CAD using CCTA, CCTA + CTP stress, CCTA + CTP-DLrest, and CCTA + CTP-DLstress was measured and compared. The time of analysis for CTP stress, CTP-DLrest, and CTP-DLStress was recorded.

Results

Patient-specific sensitivity, specificity, NPV, PPV, accuracy, and area under the curve (AUC) of CCTA alone and CCTA + CTPStress were 100%, 33%, 100%, 54%, 63%, 67% and 86%, 89%, 89%, 86%, 88%, 87%, respectively. Patient-specific sensitivity, specificity, NPV, PPV, accuracy, and AUC of CCTA + DLrest and CCTA + DLstress were 100%, 72%, 100%, 74%, 84%, 96% and 93%, 83%, 94%, 81%, 88%, 98%, respectively. All CCTA + CTP stress, CCTA + CTP-DLRest, and CCTA + CTP-DLStress significantly improved detection of hemodynamically significant CAD compared to CCTA alone (p < 0.01).

Time of CTP-DL was significantly lower as compared to human analysis (39.2 ± 3.2 vs. 379.6 ± 68.0 s, p < 0.001).

Conclusion

Evaluation of myocardial ischemia using a DL approach on rest CTP datasets is feasible and accurate. This approach may be a useful gatekeeper prior to CTP stress..

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
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Ford ES, Capewell S. Coronary heart disease mortality among young adults in the U.S. from 1980 through 2002: concealed leveling of mortality rates. J Am CollCardiol. 2007;50:2128–2132.

  2. Pontone G, Andreini D, Bartorelli AL, Bertella E, Cortinovis S, Mushtaq S, et al. A long-term prognostic value of CT angiography and exercise ECG in patients with suspected CAD. JACC Cardiovasc Imaging. 2013;6:641–50.

    Article  Google Scholar 

  3. Knuuti J, Wijns W, Saraste A, Capodanno D, Barbato E, Funck-Brentano C, et al. 2019 ESC Guidelines for the diagnosis and management of chronic coronary syndromes. Eur Heart J. 2020;41:407–77.

    Article  Google Scholar 

  4. Pontone G, Muscogiuri G, Andreini D, Guaricci AI, Guglielmo M, Mushtaq S, et al. The new frontier of cardiac computed tomography angiography: fractional flow reserve and stress myocardial perfusion. Curr Treat Options Cardiovasc Med. 2016;18:74.

    Article  Google Scholar 

  5. Pontone G, Andreini D, Guaricci AI, Baggiano A, Fazzari F, Guglielmo M, et al. Incremental diagnostic value of stress computed tomography myocardial perfusion with whole-heart coverage CT scanner in intermediate- to high-risk symptomatic patients suspected of coronary artery disease. JACC Cardiovasc Imaging. 2019;12:338–49.

    Article  Google Scholar 

  6. Pontone G, Guaricci AI, Palmer SC, Andreini D, Verdecchia M, Fusini L, et al. Diagnostic performance of non-invasive imaging for stable coronary artery disease: a meta-analysis. Int J Cardiol. 2020;300:276–81.

    Article  Google Scholar 

  7. Baggiano A, Fusini L, Del Torto A, Vivona P, Guglielmo M, Muscogiuri G, et al. Sequential strategy including FFRCT Plus Stress-CTP impacts on management of patients with stable chest pain: the stress-CTP RIPCORD study. J Clin Med. 2020;9(7):2147.

  8. Pontone G, Weir-McCall JR, Baggiano A, Del Torto A, Fusini L, Guglielmo M, et al. Determinants of rejection rate for coronary CT angiography fractional flow reserve analysis. Radiology. 2019;292:597–605.

    Article  Google Scholar 

  9. Carrascosa P, Capunay C. Myocardial CT perfusion imaging for ischemia detection. Cardiovasc Diagn Ther. 2017;7:112–28.

    Article  Google Scholar 

  10. Lee JM, Choi G, Koo BK, Hwang D, Park J, Zhang J, et al. Identification of high-risk plaques destined to cause acute coronary syndrome using coronary computed tomographic angiography and computational fluid dynamics. JACC Cardiovasc Imaging. 2019;12:1032–43.

    Article  Google Scholar 

  11. Kim SM, Cho YK, Choe YH. Adenosine-stress dynamic myocardial perfusion imaging using 128-slice dual-source CT in patients with normal body mass indices: effect of tube voltage, tube current, and iodine concentration on image quality and radiation dose. Int J Cardiovasc Imaging. 2014;30(Suppl 2):95–103.

    Article  Google Scholar 

  12. Muscogiuri G, Chiesa M, Trotta M, Gatti M, Palmisano V, Dell’Aversana S, et al. Performance of a deep learning algorithm for the evaluation of CAD-RADS classification with CCTA. Atherosclerosis. 2020;294:25–32.

    Article  CAS  Google Scholar 

  13. Al’Aref SJ, Anchouche K, Singh G, Slomka PJ, Kolli KK, Kumar A, et al. Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. Eur Heart J. 2019;40(24):1975–1986.

  14. Muscogiuri G, Van Assen M, Tesche C, De Cecco CN, Chiesa M, Scafuri S, et al. Artificial intelligence in coronary computed tomography angiography: from anatomy to prognosis. Biomed Res Int. 2020;2020:6649410.

    Article  Google Scholar 

  15. van Assen M, Muscogiuri G, Caruso D, Lee SJ, Laghi A, De Cecco CN. Artificial intelligence in cardiac radiology. Radiol Med. 2020;125:1186–99.

    Article  Google Scholar 

  16. Pontone G, Andreini D, Guaricci AI, Guglielmo M, Mushtaq S, Baggiano A, et al. Rationale and design of the PERFECTION (comparison between stress cardiac computed tomography perfusion versus fractional flow reserve measured by computed tomography angiography in the evaluation of suspected coronary artery disease) prospective study. J Cardiovasc Comput Tomogr. 2016;10:330–4.

    Article  Google Scholar 

  17. Pontone G, Baggiano A, Andreini D, Guaricci AI, Guglielmo M, Muscogiuri G, et al. Stress computed tomography perfusion versus fractional flow reserve CT derived in suspected coronary artery disease: the PERFECTION study. JACC Cardiovasc Imaging. 2019;12:1487–97.

    Article  Google Scholar 

  18. Abbara S, Blanke P, Maroules CD, Cheezum M, Choi AD, Han BK, et al. 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. 2016;10:435–49.

    Article  Google Scholar 

  19. Pontone G, Muscogiuri G, Andreini D, Guaricci AI, Guglielmo M, Baggiano A, et al. Impact of a new adaptive statistical iterative reconstruction (ASIR)-V algorithm on image quality in coronary computed tomography angiography. Acad Radiol. 2018;25:1305–13.

    Article  Google Scholar 

  20. Pontone G, Moharem-Elgamal S, Maurovich-Horvat P, Gaemperli O, Pugliese F, Westwood M, et al. Training in cardiac computed tomography: EACVI certification process. Eur Heart J Cardiovasc Imaging. 2018;19:123–6.

    Article  Google Scholar 

  21. Austen WG, Edwards JE, Frye RL, Gensini GG, Gott VL, Griffith LS, et al. A reporting system on patients evaluated for coronary artery disease. Report of the Ad Hoc Committee for Grading of Coronary Artery Disease, Council on Cardiovascular Surgery, American Heart Association. Circulation. 1975;51:5–40.

  22. Cerqueira MD, Weissman NJ, Dilsizian V, Jacobs AK, Kaul S, Laskey WK, et al. Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart. A statement for healthcare professionals from the Cardiac Imaging Committee of the Council on Clinical Cardiology of the American Heart Association. Circulation. 2002;105:539–542.

  23. Cerci RJ, Arbab-Zadeh A, George RT, Miller JM, Vavere AL, Mehra V, et al. Aligning coronary anatomy and myocardial perfusion territories: an algorithm for the CORE320 multicenter study. Circ Cardiovasc Imaging. 2012;5:587–95.

    Article  Google Scholar 

  24. Levine GN, Bates ER, Blankenship JC, Bailey SR, Bittl JA, Cercek B, et al. 2011 ACCF/AHA/SCAI Guideline for percutaneous coronary intervention. A report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines and the Society for Cardiovascular Angiography and Interventions. J Am Coll Cardiol. 2011;58:e44–e122.

  25. Tonino PA, De Bruyne B, Pijls NH, Siebert U, Ikeno F, van' t Veer M, et al. Fractional flow reserve versus angiography for guiding percutaneous coronary intervention. N Engl J Med. 2009;360:213–224.

  26. Svrivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15(56):1929−1958.

  27. Nair V, Hinton G. Rectified linear units improve restricted Boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning-New York: ACM. 2010:807–814.

  28. Xiong G, Kola D, Heo R, Elmore K, Cho I, Min JK. Myocardial perfusion analysis in cardiac computed tomography angiographic images at rest. Med Image Anal. 2015;24:77–89.

    Article  Google Scholar 

  29. van Hamersvelt RW, Zreik M, Voskuil M, Viergever MA, Isgum I, Leiner T. Deep learning analysis of left ventricular myocardium in CT angiographic intermediate-degree coronary stenosis improves the diagnostic accuracy for identification of functionally significant stenosis. Eur Radiol. 2019;29:2350–9.

    Article  Google Scholar 

Download references

Author information

Author notes

  1. Giuseppe Muscogiuri and Mattia Chiesa are contributed equally

Authors and Affiliations

  1. Centro Cardiologico Monzino, IRCCS, Milan, Italy

    Giuseppe Muscogiuri, Mattia Chiesa, Andrea Baggiano, Marco Guglielmo, Stefano Scafuri, Laura Fusini, Saima Mushtaq, Edoardo Conte, Andrea Annoni, Alberto Formenti, Maria Elisabetta Mancini, Francesca Ricci, Francesco Paolo Ariano, Luigi Spiritigliozzi, Mario Babbaro, Rocco Mollace, Riccardo Maragna, Carlo Maria Giacari, Daniele Andreini, Gualtiero I. Colombo, Mauro Pepi & Gianluca Pontone

  2. Department of Electronics, Information and Biomedical Engineering, Politecnico di Milano, 20133, Milan, Italy

    Mattia Chiesa & Francesco Sardanelli

  3. Department of Biomedical Sciences for Health, University of Milan, Milan, Italy

    Pierino Spadafora & Rossella De Santis

  4. Department of Clinical Sciences and Community Health, Cardiovascular Section, University of Milan, Milan, Italy

    Daniele Andreini

  5. Department of Emergency and Organ Transplantation, Institute of Cardiovascular Disease, University Hospital “Policlinico Consorziale” of Bari, Bari, Italy

    Andrea Igoren Guaricci

  6. Loyola University of Chicago, Chicago, IL, USA

    Mark G. Rabbat

  7. Edward Hines Jr. VA Hospital, Hines, IL, USA

    Mark G. Rabbat

  8. Unit of Radiology, IRCCS Policlinico San Donato, San Donato Milanese, Milan, Italy

    Francesco Sardanelli

Authors
  1. Giuseppe Muscogiuri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mattia Chiesa
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Andrea Baggiano
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Pierino Spadafora
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Rossella De Santis
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Marco Guglielmo
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Stefano Scafuri
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Laura Fusini
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Saima Mushtaq
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Edoardo Conte
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Andrea Annoni
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Alberto Formenti
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Maria Elisabetta Mancini
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Francesca Ricci
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Francesco Paolo Ariano
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Luigi Spiritigliozzi
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Mario Babbaro
    View author publications

    You can also search for this author in PubMed Google Scholar

  18. Rocco Mollace
    View author publications

    You can also search for this author in PubMed Google Scholar

  19. Riccardo Maragna
    View author publications

    You can also search for this author in PubMed Google Scholar

  20. Carlo Maria Giacari
    View author publications

    You can also search for this author in PubMed Google Scholar

  21. Daniele Andreini
    View author publications

    You can also search for this author in PubMed Google Scholar

  22. Andrea Igoren Guaricci
    View author publications

    You can also search for this author in PubMed Google Scholar

  23. Gualtiero I. Colombo
    View author publications

    You can also search for this author in PubMed Google Scholar

  24. Mark G. Rabbat
    View author publications

    You can also search for this author in PubMed Google Scholar

  25. Mauro Pepi
    View author publications

    You can also search for this author in PubMed Google Scholar

  26. Francesco Sardanelli
    View author publications

    You can also search for this author in PubMed Google Scholar

  27. Gianluca Pontone
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Gianluca Pontone.

Ethics declarations

Informed consent

Informed consent was obtained from all individual participants included in the study. Patients signed informed consent regarding publishing their data and photographs.

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's Note

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

This article is part of the Topical Collection on Cardiology

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Muscogiuri, G., Chiesa, M., Baggiano, A. et al. Diagnostic performance of deep learning algorithm for analysis of computed tomography myocardial perfusion. Eur J Nucl Med Mol Imaging 49, 3119–3128 (2022). https://doi.org/10.1007/s00259-022-05732-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00259-022-05732-w

Keywords

Search

Navigation