Diagnostic Performance of an Artificial Intelligence-driven Cardiac-structured Reporting System for Myocardial Perfusion SPECT Imaging

Overview

Journal J Nucl Cardiol

Specialty Cardiology & Vascular Diseases

Date 2018 Sep 14

PMID 30209754

Citations 10

Authors

Ernest V Garcia

J Larry Klein

Valeria Moncayo

C David Cooke

Christian DelAune

Russell Folks

Liudmila Verdes Moreiras

Fabio Esteves

Affiliations

Soon will be listed here.

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.

Citing Articles

Advancements in artificial intelligence-driven techniques for interventional cardiology.

Rudnicka Z, Pregowska A, Gladys K, Perkins M, Proniewska K Cardiol J. 2024; 31(2):321-341.

PMID: 38247435 PMC: 11076027. DOI: 10.5603/cj.98650.

Diagnosis of diffuse ischemia with SPECT relative perfusion imaging: How to eat soup with a fork?.

Hulten E, Keating F J Nucl Cardiol. 2023; 30(5):2039-2042.

PMID: 37193922 DOI: 10.1007/s12350-023-03286-4.

Preparing for the Artificial Intelligence Revolution in Nuclear Cardiology.

Garcia E, Piccinelli M Nucl Med Mol Imaging. 2023; 57(2):51-60.

PMID: 36998588 PMC: 10043081. DOI: 10.1007/s13139-021-00733-3.

Quantitation of diffuse myocardial ischemia with mental stress and its association with cardiovascular events in individuals with recent myocardial infarction.

Almuwaqqat Z, Garcia E, Cooke C, Garcia M, Shah A, Elon L J Nucl Cardiol. 2023; 30(5):2029-2038.

PMID: 36991249 PMC: 11057358. DOI: 10.1007/s12350-023-03212-8.

Integrating artificial intelligence and natural language processing for computer-assisted reporting and report understanding in nuclear cardiology.

Garcia E J Nucl Cardiol. 2022; 30(3):1180-1190.

PMID: 35725887 DOI: 10.1007/s12350-022-02996-5.

References

Esteves F, Raggi P, Folks R, Keidar Z, Askew J, Rispler S . Novel solid-state-detector dedicated cardiac camera for fast myocardial perfusion imaging: multicenter comparison with standard dual detector cameras. J Nucl Cardiol. 2009; 16(6):927-34. PMC: 2776146. DOI: 10.1007/s12350-009-9137-2. View

Arsanjani R, Xu Y, Dey D, Vahistha V, Shalev A, Nakanishi R . Improved accuracy of myocardial perfusion SPECT for detection of coronary artery disease by machine learning in a large population. J Nucl Cardiol. 2013; 20(4):553-62. PMC: 3732038. DOI: 10.1007/s12350-013-9706-2. View

Taylor A, Hill A, Binongo J, Manatunga A, Halkar R, Dubovsky E . Evaluation of two diuresis renography decision support systems to determine the need for furosemide in patients with suspected obstruction. AJR Am J Roentgenol. 2007; 188(5):1395-402. PMC: 3694351. DOI: 10.2214/AJR.06.0931. View

Garcia E, Taylor A, Folks R, Manatunga D, Halkar R, Savir-Baruch B . 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(9):1483-91. PMC: 3688257. DOI: 10.1007/s00259-012-2151-7. View

Hansen C, Goldstein R, Akinboboye O, Berman D, Botvinick E, Churchwell K . Myocardial perfusion and function: single photon emission computed tomography. J Nucl Cardiol. 2007; 14(6):e39-60. DOI: 10.1016/j.nuclcard.2007.09.023. View

Esteves F, Galt J, Folks R, Verdes L, Garcia E . 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. 2013; 21(1):158-65. DOI: 10.1007/s12350-013-9827-7. View

Tilkemeier P, Cooke C, Ficaro E, Glover D, Hansen C, McCallister Jr B . American Society of Nuclear Cardiology information statement: Standardized reporting matrix for radionuclide myocardial perfusion imaging. J Nucl Cardiol. 2006; 13(6):e157-71. DOI: 10.1016/j.nuclcard.2006.08.014. View

Douglas P, Hendel R, Cummings J, Dent J, Hodgson J, Hoffmann U . ACCF/ACR/AHA/ASE/ASNC/HRS/NASCI/RSNA/SAIP/SCAI/SCCT/SCMR 2008 Health Policy Statement on Structured Reporting in Cardiovascular Imaging. J Am Coll Cardiol. 2009; 53(1):76-90. DOI: 10.1016/j.jacc.2008.09.005. View

Haddad M, Adlassnig K, 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(1):61-78. DOI: 10.1016/s0933-3657(96)00361-2. View

10.

Fujita H, Katafuchi T, Uehara T, Nishimura T . Application of artificial neural network to computer-aided diagnosis of coronary artery disease in myocardial SPECT bull's-eye images. J Nucl Med. 1992; 33(2):272-6. View

11.

Arsanjani R, Xu Y, Dey D, Fish M, Dorbala S, Hayes S . Improved accuracy of myocardial perfusion SPECT for the detection of coronary artery disease using a support vector machine algorithm. J Nucl Med. 2013; 54(4):549-55. PMC: 3615055. DOI: 10.2967/jnumed.112.111542. View

12.

Cerqueira M, Weissman N, Dilsizian V, Jacobs A, Kaul S, Laskey W . 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(4):539-42. DOI: 10.1161/hc0402.102975. View

13.

Rozanski A, Gransar H, Hayes S, Min J, Friedman J, Thomson L . Temporal trends in the frequency of inducible myocardial ischemia during cardiac stress testing: 1991 to 2009. J Am Coll Cardiol. 2013; 61(10):1054-65. DOI: 10.1016/j.jacc.2012.11.056. View

14.

Garcia E, Cooke C, Folks R, Santana C, Krawczynska E, De Braal L . Diagnostic performance of an expert system for the interpretation of myocardial perfusion SPECT studies. J Nucl Med. 2001; 42(8):1185-91. View

15.

Chhabra L, Ahlberg A, Henzlova M, Duvall W . Temporal trends of stress myocardial perfusion imaging: Influence of diabetes, gender and coronary artery disease status. Int J Cardiol. 2015; 202:922-9. DOI: 10.1016/j.ijcard.2015.09.020. View

16.

Garcia E, Faber T, Cooke C, Folks R, Chen J, Santana C . The increasing role of quantification in clinical nuclear cardiology: the Emory approach. J Nucl Cardiol. 2007; 14(4):420-32. DOI: 10.1016/j.nuclcard.2007.06.009. View

17.

Hamilton D, Riley P, Miola U, Amro A . A feed forward neural network for classification of bull's-eye myocardial perfusion images. Eur J Nucl Med. 1995; 22(2):108-15. DOI: 10.1007/BF00838939. View

18.

LINDAHL D, Lanke J, Lundin A, Palmer J, Edenbrandt L . Improved classifications of myocardial bull's-eye scintigrams with computer-based decision support system. J Nucl Med. 1999; 40(1):96-101. View

19.

Garcia E, 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(3):463-70. PMC: 3695612. View

20.

Ladapo J, Blecker S, Elashoff M, Federspiel J, Vieira D, Sharma G . Clinical implications of referral bias in the diagnostic performance of exercise testing for coronary artery disease. J Am Heart Assoc. 2013; 2(6):e000505. PMC: 3886773. DOI: 10.1161/JAHA.113.000505. View