Skip to main content

Advertisement

SpringerLink
Log in

Diagnostic performance of an artificial intelligence-driven cardiac-structured reporting system for myocardial perfusion SPECT imaging

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

Abstract

Objectives

To describe and validate an artificial intelligence (AI)-driven structured reporting system by direct comparison of automatically generated reports to results from actual clinical reports generated by nuclear cardiology experts.

Background

Quantitative parameters extracted from myocardial perfusion imaging (MPI) studies are used by our AI reporting system to generate automatically a guideline-compliant structured report (sR).

Method

A new nonparametric approach generates distribution functions of rest and stress, perfusion, and thickening, for each of 17 left ventricle segments that are then transformed to certainty factors (CFs) that a segment is hypoperfused, ischemic. These CFs are then input to our set of heuristic rules used to reach diagnostic findings and impressions propagated into a sR referred as an AI-driven structured report (AIsR).

The diagnostic accuracy of the AIsR for detecting coronary artery disease (CAD) and ischemia was tested in 1,000 patients who had undergone rest/stress SPECT MPI.

Results

At the high-specificity (SP) level, in a subset of 100 patients, there were no statistical differences in the agreements between the AIsr, and nine experts’ impressions of CAD (P = .33) or ischemia (P = .37). This high-SP level also yielded the highest accuracy across global and regional results in the 1,000 patients. These accuracies were statistically significantly better than the other two levels [sensitivity (SN)/SP tradeoff, high SN] across all comparisons.

Conclusions

This AI reporting system automatically generates a structured natural language report with a diagnostic performance comparable to those of experts.

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
Figure 4
Figure 5

Similar content being viewed by others

Abbreviations

AI:

Artificial intelligence

AIsR:

AI-driven structured report

CAD:

Coronary artery disease

CF:

Certainty factor

CI:

Confidence interval

ECTb:

Emory Cardiac Toolbox

LAD:

Left anterior descending coronary artery

LCX:

Left circumflex coronary artery

LLK:

Low likelihood

LV:

Left ventricle

MPI:

Myocardial perfusion imaging

NC:

Nuclear cardiology

RCA:

Right coronary artery

TID:

Trans-ischemic dilatation

SN:

Sensitivity

SP:

Specificity

sRs:

Structured report

SSS:

Sum stress score

References

  1. Fujita H, Katafuchi T, Uehara T, Nishimura T. Application of neural network to computer-aided diagnosis of coronary artery disease in myocardial SPECT Bull’s-eye images. J Nucl Med. 1992;33:272–6.

    CAS  Google Scholar 

  2. Porenta G, Dorffner G, Kundrat S, Petta P, Duit-Schedlmayer J, Sochor H. Automated interpretation of planar thallium-201-dipyridamole stress-redistribution scintigrams using artificial neural networks. J Nucl Med. 1994;35:2041–7.

    CAS  Google Scholar 

  3. Hamilton D, Riley PJ, Miola UJ, Amro AA. A feed forward neural network for classification of bull’s-eye myocardial perfusion images. Eur J Nucl Med. 1995;22:108–15.

    Article  CAS  PubMed Central  Google Scholar 

  4. Lindahl D, Lanke J, Lundin A, Palmer J, Edenbradt L. Improved classifications of myocardial bull’s-eye scintigrams with computer-based decision support system. J Nucl Med. 1999;40:96–101.

    CAS  Google Scholar 

  5. Haddad M, Adlassnig KP, Porenta G. Feasibility analysis of a case-based reasoning system for automated detection of coronary heart disease from myocardial scintigrams. Artif Intell Med. 1997;9:61–78.

    Article  CAS  PubMed Central  Google Scholar 

  6. Arsanjani RA, Xu Y, Dey D, Fish M, Dorbala S, Hayes S, et al. Improved accuracy of myocardial perfusion SPECT for the detection of coronary artery disease using a support vector machine algorithm. J Nucl Med. 2013;54:549–55.

    Article  PubMed Central  Google Scholar 

  7. Arsanjani RA, Xu Y, Dey D, Vahistha V, Nakanishi R, Hayes S, et al. Improved accuracy of myocardial perfusion SPECT for detection of coronary artery disease by machine learning in a large population. J Nucl Cardiol. 2013;20:553–62.

    Article  PubMed Central  Google Scholar 

  8. Ezquerra N, Mullick R, Cooke D, Krawczynska E, Garcia E. PERFEX: An expert system for interpreting 3D myocardial perfusion. Expert Syst Appl. 1993;6:459–68.

    Article  Google Scholar 

  9. Garcia EV, Cooke CD, Folks RD, Santana CA, Krawczynska EG, De Braal L, et al. Diagnostic performance of an expert system for the interpretation of myocardial perfusion SPECT studies. J Nucl Med. 2001;42:1185–91.

    CAS  Google Scholar 

  10. Douglas PS, Hendel RC, Cummings JE, Dent JM, Hodgson JM, Hoffmann U, et al. ACCF/ACR/AHA/ASE/ASNC/HRS/NASCI/RSNA/SAIP/SCAI/SCCT/SCMR 2008 health policy statement on structured reporting in cardiovascular imaging. JACC. 2009;53:76–90.

    Article  Google Scholar 

  11. Hansen CL, Richard A. Goldstein (Co-chairs): Myocardial perfusion and function: Single photon emission computed tomography. ASNC guidelines for nuclear cardiology procedures. J Nucl Cardiol. 2007;14:e39–60.

    Article  Google Scholar 

  12. Garcia EV, Faber TL, Cooke CD, Folks RD, Chen J, Santana C. The increasing role of quantification in nuclear cardiology: The Emory approach. J Nucl Cardiol. 2007;14:420–32.

    Article  PubMed Central  Google Scholar 

  13. 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. Circulation. 2002;105:539–42.

    Article  Google Scholar 

  14. Esteves FP, Raggi P, Folks RD, Keidar Z, Askew JW, Rispler S, et al. Novel solid-state-detector dedicated cardiac camera for fast myocardial perfusion imaging: Multicenter comparison with standard dual detector cameras. J Nucl Cardiol. 2009;16:927–34.

    Article  PubMed Central  Google Scholar 

  15. Esteves FP, Galt JR, Folks RD, Verdes L, Garcia EV. Diagnostic performance of low-dose rest/stress Tc-99m tetrofosmin myocardial perfusion SPECT using the 530c CZT camera: Quantitative vs. visual analysis. J Nucl Cardiol. 2014;21:158–65.

    Article  Google Scholar 

  16. Shannon EC, Weaver W. The mathematical theory of communication. Chicago: University of Illinois Press; 1949.

    Google Scholar 

  17. Shortliffe EH. Computer-based medical consultations: MYCIN. Amsterdam: Elsevier Scientific Publishing Company; 1976. p. 264.

    Google Scholar 

  18. Tilkemeier PL, Cooke CD, Grossman GB, McCallister BD, Ward RP. Standardized reporting of myocardial perfusion and function. J Nucl Cardiol. 2009. https://doi.org/10.1007/s12350-009-9095-8.

    Article  Google Scholar 

  19. Dunn OJ. Basic statistics: A primer for the biomedical sciences. New York: Wiley; 1977. p. 116–9.

    Google Scholar 

  20. Chhabra L, Ahlberg AW, Henzlova MJ, Duvall WL. Temporal trends of stress myocardial perfusion imaging: Influence of diabetes, gender and coronary artery disease status. Int J Cardiol. 2016. https://doi.org/10.1016/j.ijcard.2015.09.020.

    Article  Google Scholar 

  21. Rozanski A, Gransar H, Hayes SW, Min J, Friedman JD, Thomson LEJ, et al. Temporal trends in the frequency of inducible myocardial ischemia during cardiac stress testing: 1991 to 2009. JACC. 2013;10:1054–65.

    Article  Google Scholar 

  22. Ladapo JA, Blecker S, Elashoff MR, Federspiel JJ, Vieira DL, Sharma G, et al. Clinical implications of referral bias in the diagnostic performance of exercise testing for coronary artery disease. J Am Heart Assoc. 2013;2:e000505. https://doi.org/10.1161/jaha113.000505.

    Article  PubMed Central  Google Scholar 

  23. Garcia EV, Taylor A, Manatunga D, Folks R. A software engine to justify the conclusions of an expert system for detecting renal obstruction on 99mTc-MAG3 scans. J Nucl Med. 2007;48:463–70.

    PubMed Central  Google Scholar 

  24. Taylor A, Hill A, Binongo J, Manatunga A, Halkar R, Dubovsky EV, Garcia EV. Evaluation of two diuresis renography decision support systems designed to determine the need for furosemide in patients with suspected obstruction. AJR. 2007;188:1395–402.

    Article  Google Scholar 

  25. Garcia EV, Taylor A, Folks R, Manatunga D, Halkar R, Savir-Baruch B, et al. iRENEX: A clinically informed decision support system for the interpretation of 99mTc-MAG3 scans to detect renal obstruction. Eur J Nucl Med Mol Imaging. 2012;39:1483–91. https://doi.org/10.1007/s00259-012-2151-7.

    Article  PubMed Central  Google Scholar 

Download references

Acknowledgments

This work was supported by the NHLBI Grant Number R42HL106818. The authors acknowledge Emory University Hospital Nuclear Cardiology Diagnosticians for allowing the use of their clinical MPI reports as well as Archana Kudrimoti for data mining the data warehouse for the clinical data reported.

Disclosures

EVG, CDC, RF, and JLK receive royalties from the sale of the Emory Cardiac Toolbox and/or Smart Report described in this article. The terms of this arrangement have been reviewed and approved by Emory University in accordance with its COI practice. CDA and CDC are employees of or consultants to Syntermed. All other authors report no conflicts of interest.

Author information

Authors and Affiliations

  1. Department of Radiology and Imaging Sciences, Emory University, 101 Woodruff Circle, Room 1203, Atlanta, GA, 30322, USA

    Ernest V. Garcia PhD, Valeria Moncayo MD, C. David Cooke MSEE, Russell Folks CNMT, Liudmila Verdes Moreiras MSN & Fabio Esteves MD

  2. Division of Cardiology, Department of Medicine, UNC School of Medicine, University of North Carolina, Chapel Hill, NC, USA

    J. Larry Klein MD

  3. Syntermed, Inc., Atlanta, GA, USA

    C. David Cooke MSEE & Christian Del’Aune BSEE

Authors
  1. Ernest V. Garcia PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. Larry Klein MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Valeria Moncayo MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. C. David Cooke MSEE
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Christian Del’Aune BSEE
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Russell Folks CNMT
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Liudmila Verdes Moreiras MSN
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Fabio Esteves MD
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ernest V. Garcia PhD.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (PPTX 507 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Garcia, E.V., Klein, J.L., Moncayo, V. et al. Diagnostic performance of an artificial intelligence-driven cardiac-structured reporting system for myocardial perfusion SPECT imaging. J. Nucl. Cardiol. 27, 1652–1664 (2020). https://doi.org/10.1007/s12350-018-1432-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12350-018-1432-3

Keywords

Search

Navigation