Skip to main content
Top
Published in: European Journal of Nuclear Medicine and Molecular Imaging 9/2022

21-03-2022 | Original Article

“Virtual” attenuation correction: improving stress myocardial perfusion SPECT imaging using deep learning

Authors: Tomoe Hagio, Alexis Poitrasson-Rivière, Jonathan B. Moody, Jennifer M. Renaud, Liliana Arida-Moody, Ravi V. Shah, Edward P. Ficaro, Venkatesh L. Murthy

Published in: European Journal of Nuclear Medicine and Molecular Imaging | Issue 9/2022

Login to get access

Abstract

Purpose

Myocardial perfusion imaging (MPI) using single-photon emission computed tomography (SPECT) is widely used for coronary artery disease (CAD) evaluation. Although attenuation correction is recommended to diminish image artifacts and improve diagnostic accuracy, approximately 3/4ths of clinical MPI worldwide remains non-attenuation-corrected (NAC). In this work, we propose a novel deep learning (DL) algorithm to provide “virtual” DL attenuation–corrected (DLAC) perfusion polar maps solely from NAC data without concurrent computed tomography (CT) imaging or additional scans.

Methods

SPECT MPI studies (N = 11,532) with paired NAC and CTAC images were retrospectively identified. A convolutional neural network–based DL algorithm was developed and trained on half of the population to predict DLAC polar maps from NAC polar maps. Total perfusion deficit (TPD) was evaluated for all polar maps. TPDs from NAC and DLAC polar maps were compared to CTAC TPDs in linear regression analysis. Moreover, receiver-operating characteristic analysis was performed on NAC, CTAC, and DLAC TPDs to predict obstructive CAD as diagnosed from invasive coronary angiography.

Results

DLAC TPDs exhibited significantly improved linear correlation (p < 0.001) with CTAC (R2 = 0.85) compared to NAC vs. CTAC (R2 = 0.68). The diagnostic performance of TPD was also improved with DLAC compared to NAC with an area under the curve (AUC) of 0.827 vs. 0.780 (p = 0.012) with no statistically significant difference between AUC for CTAC and DLAC. At 88% sensitivity, specificity was improved by 18.9% for DLAC and 25.6% for CTAC.

Conclusions

The proposed DL algorithm provided attenuation correction comparable to CTAC without the need for additional scans. Compared to conventional NAC perfusion imaging, DLAC significantly improved diagnostic accuracy.
Appendix
Available only for authorised users
Literature
1.
go back to reference Hendel RC, Corbett JR, Cullom SJ, DePuey EG, Garcia EV, Bateman TM. The value and practice of attenuation correction for myocardial perfusion SPECT imaging: a joint position statement from the American Society of Nuclear Cardiology and the Society of Nuclear Medicine. J Nucl Cardiol. 2002;9:135–43.CrossRef Hendel RC, Corbett JR, Cullom SJ, DePuey EG, Garcia EV, Bateman TM. The value and practice of attenuation correction for myocardial perfusion SPECT imaging: a joint position statement from the American Society of Nuclear Cardiology and the Society of Nuclear Medicine. J Nucl Cardiol. 2002;9:135–43.CrossRef
2.
go back to reference Ficaro EP, Fessler JA, Shreve PD, Kritzman JN, Rose PA, Corbett JR. Simultaneous transmission/emission myocardial perfusion tomography. Circulation. 1996;93:463–73.CrossRef Ficaro EP, Fessler JA, Shreve PD, Kritzman JN, Rose PA, Corbett JR. Simultaneous transmission/emission myocardial perfusion tomography. Circulation. 1996;93:463–73.CrossRef
3.
go back to reference Huang JY, Huang CK, Yen RF, Wu HY, Tu YK, Cheng MF, et al. Diagnostic performance of attenuation-corrected myocardial perfusion imaging for coronary artery disease a systematic review and meta-analysis. J Nucl Med Society of Nuclear Medicine Inc. 2016;57:1893–8. Huang JY, Huang CK, Yen RF, Wu HY, Tu YK, Cheng MF, et al. Diagnostic performance of attenuation-corrected myocardial perfusion imaging for coronary artery disease a systematic review and meta-analysis. J Nucl Med Society of Nuclear Medicine Inc. 2016;57:1893–8.
4.
go back to reference Hirschfeld CB, Mercuri M, Pascual TNB, Karthikeyan G, Vitola J V, Mahmarian JJ, et al. Worldwide variation in the use of nuclear cardiology camera technology, reconstruction software, and imaging protocols. JACC Cardiovasc Imaging (2021) Hirschfeld CB, Mercuri M, Pascual TNB, Karthikeyan G, Vitola J V, Mahmarian JJ, et al. Worldwide variation in the use of nuclear cardiology camera technology, reconstruction software, and imaging protocols. JACC Cardiovasc Imaging (2021)
5.
go back to reference Shen D, Wu G, Suk H-I. Deep learning in medical image analysis. Annu Rev Biomed Eng Annual Reviews. 2017;19:221–48.CrossRef Shen D, Wu G, Suk H-I. Deep learning in medical image analysis. Annu Rev Biomed Eng Annual Reviews. 2017;19:221–48.CrossRef
6.
go back to reference Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med. Image Anal. Elsevier B.V.; (2017) 60–88. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med. Image Anal. Elsevier B.V.; (2017) 60–88.
7.
go back to reference Betancur J, Commandeur F, Motlagh M, Sharir T, Einstein AJ, Bokhari S, et al. Deep learning for prediction of obstructive disease from fast myocardial perfusion SPECT: a multicenter study. JACC Cardiovasc Imaging Elsevier Inc. 2018;11:1654–63.CrossRef Betancur J, Commandeur F, Motlagh M, Sharir T, Einstein AJ, Bokhari S, et al. Deep learning for prediction of obstructive disease from fast myocardial perfusion SPECT: a multicenter study. JACC Cardiovasc Imaging Elsevier Inc. 2018;11:1654–63.CrossRef
8.
go back to reference Yang J, Shi L, Wang R, Miller EJ, Sinusas AJ, Liu CJ, et al. Direct attenuation correction using deep learning for cardiac SPECT: a feasibility study. J Nucl Med. 2021;120:256396 (jnumed). Yang J, Shi L, Wang R, Miller EJ, Sinusas AJ, Liu CJ, et al. Direct attenuation correction using deep learning for cardiac SPECT: a feasibility study. J Nucl Med. 2021;120:256396 (jnumed).
9.
go back to reference Shi L, Onofrey JA, Liu H, Liu YH, Liu C. Deep learning-based attenuation map generation for myocardial perfusion SPECT. Eur J Nucl Med Mol Imaging: Springer; 2020.CrossRef Shi L, Onofrey JA, Liu H, Liu YH, Liu C. Deep learning-based attenuation map generation for myocardial perfusion SPECT. Eur J Nucl Med Mol Imaging: Springer; 2020.CrossRef
10.
go back to reference Géron A Hands-on machine learning with Scikit-Learn and TensorFlow: concepts, tools, and techniques to build intelligent systems. O’Reilly Media (2017) Géron A Hands-on machine learning with Scikit-Learn and TensorFlow: concepts, tools, and techniques to build intelligent systems. O’Reilly Media (2017)
11.
go back to reference Dorbala S, Ananthasubramaniam K, Armstrong IS, Chareonthaitawee P, DePuey EG, Einstein AJ, et al. Single photon emission computed tomography (SPECT) myocardial perfusion imaging guidelines: instrumentation, acquisition, processing, and interpretation. J Nucl Cardiol Springer New York LLC. 2018;25:1784–846.CrossRef Dorbala S, Ananthasubramaniam K, Armstrong IS, Chareonthaitawee P, DePuey EG, Einstein AJ, et al. Single photon emission computed tomography (SPECT) myocardial perfusion imaging guidelines: instrumentation, acquisition, processing, and interpretation. J Nucl Cardiol Springer New York LLC. 2018;25:1784–846.CrossRef
12.
go back to reference Ficaro EP, Lee BC, Kritzman JN, Corbett JR. Corridor4DM: the Michigan method for quantitative nuclear cardiology. J Nucl Cardiol. 2007;14:455–65.CrossRef Ficaro EP, Lee BC, Kritzman JN, Corbett JR. Corridor4DM: the Michigan method for quantitative nuclear cardiology. J Nucl Cardiol. 2007;14:455–65.CrossRef
13.
go back to reference Dice LR. Measures of the amount of ecologic association between species. Ecology Wiley. 1945;26:297–302.CrossRef Dice LR. Measures of the amount of ecologic association between species. Ecology Wiley. 1945;26:297–302.CrossRef
14.
go back to reference Slomka PJ, Nishina H, Berman DS, Akincioglu C, Abidov A, Friedman JD, et al. Automated quantification of myocardial perfusion SPECT using simplified normal limits. J Nucl Cardiol. 2005;12:66–77 (No longer published by Elsevier).CrossRef Slomka PJ, Nishina H, Berman DS, Akincioglu C, Abidov A, Friedman JD, et al. Automated quantification of myocardial perfusion SPECT using simplified normal limits. J Nucl Cardiol. 2005;12:66–77 (No longer published by Elsevier).CrossRef
15.
go back to reference Slomka PJ, Fish MB, Lorenzo S, Nishina H, Gerlach J, Berman DS, et al. Simplified normal limits and automated quantitative assessment for attenuation-corrected myocardial perfusion SPECT. J Nucl Cardiol United States. 2006;13:642–51.CrossRef Slomka PJ, Fish MB, Lorenzo S, Nishina H, Gerlach J, Berman DS, et al. Simplified normal limits and automated quantitative assessment for attenuation-corrected myocardial perfusion SPECT. J Nucl Cardiol United States. 2006;13:642–51.CrossRef
16.
go back to reference Nakazato R, Tamarappoo BK, Kang X, Wolak A, Kite F, Hayes SW, et al. Quantitative upright–supine high-speed SPECT myocardial perfusion imaging for detection of coronary artery disease: correlation with invasive coronary angiography. J Nucl Med. 2010;51:1724 LP – 1731.CrossRef Nakazato R, Tamarappoo BK, Kang X, Wolak A, Kite F, Hayes SW, et al. Quantitative upright–supine high-speed SPECT myocardial perfusion imaging for detection of coronary artery disease: correlation with invasive coronary angiography. J Nucl Med. 2010;51:1724 LP – 1731.CrossRef
17.
go back to reference Garcia EV, Slomka P, Moody JB, Germano G, Ficaro EP. Quantitative clinical nuclear cardiology, part 1: established applications. J Nucl Med Society of Nuclear Medicine Inc. 2019;60:1507–16. Garcia EV, Slomka P, Moody JB, Germano G, Ficaro EP. Quantitative clinical nuclear cardiology, part 1: established applications. J Nucl Med Society of Nuclear Medicine Inc. 2019;60:1507–16.
18.
go back to reference Goetze S, Wahl RL. Prevalence of misregistration between SPECT and CT for attenuation-corrected myocardial perfusion SPECT. J Nucl Cardiol. 2007;14:200.CrossRef Goetze S, Wahl RL. Prevalence of misregistration between SPECT and CT for attenuation-corrected myocardial perfusion SPECT. J Nucl Cardiol. 2007;14:200.CrossRef
19.
go back to reference Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WFA, editors. Med Image Comput Comput Interv – MICCAI 2015 Lect Notes Comput Sci. Springer: Cham; 2015. p. 234–41. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WFA, editors. Med Image Comput Comput Interv – MICCAI 2015 Lect Notes Comput Sci. Springer: Cham; 2015. p. 234–41.
20.
go back to reference Genders TSS, Steyerberg EW, Hunink MGM, Nieman K, Galema TW, Mollet NR, et al. Prediction model to estimate presence of coronary artery disease: retrospective pooled analysis of existing cohorts. BMJ. BMJ Publishing Group Ltd (2012) 344 Genders TSS, Steyerberg EW, Hunink MGM, Nieman K, Galema TW, Mollet NR, et al. Prediction model to estimate presence of coronary artery disease: retrospective pooled analysis of existing cohorts. BMJ. BMJ Publishing Group Ltd (2012) 344
21.
go back to reference DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics JSTOR. 1988;44:837.CrossRef DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics JSTOR. 1988;44:837.CrossRef
22.
go back to reference McNemar Q. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika Springer-Verlag. 1947;12:153–7.CrossRef McNemar Q. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika Springer-Verlag. 1947;12:153–7.CrossRef
23.
go back to reference Edwards AL. Note on the “correction for continuity” in testing the significance of the difference between correlated proportions. Psychometrika Springer-Verlag. 1948;13:185–7.CrossRef Edwards AL. Note on the “correction for continuity” in testing the significance of the difference between correlated proportions. Psychometrika Springer-Verlag. 1948;13:185–7.CrossRef
24.
go back to reference Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez JC, et al. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinforma 2011 121. BioMed Central. 2011;12:1–8. Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez JC, et al. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinforma 2011 121. BioMed Central. 2011;12:1–8.
25.
go back to reference Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, et al. Intriguing properties of neural networks. 2nd Int Conf Learn Represent ICLR 2014 - Conf Track Proc. ICLR (2014) Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, et al. Intriguing properties of neural networks. 2nd Int Conf Learn Represent ICLR 2014 - Conf Track Proc. ICLR (2014)
26.
go back to reference Antun V, Renna F, Poon C, Adcock B, Hansen AC On instabilities of deep learning in image reconstruction and the potential costs of AI. Proc Natl Acad Sci. Proceedings of the National Academy of Sciences; (2020) 201907377 Antun V, Renna F, Poon C, Adcock B, Hansen AC On instabilities of deep learning in image reconstruction and the potential costs of AI. Proc Natl Acad Sci. Proceedings of the National Academy of Sciences; (2020) 201907377
27.
go back to reference Serre T. Deep learning: the good, the bad, and the ugly. Annu Rev Vis Sci Annual Reviews. 2019;5:399–426.CrossRef Serre T. Deep learning: the good, the bad, and the ugly. Annu Rev Vis Sci Annual Reviews. 2019;5:399–426.CrossRef
Metadata
Title
“Virtual” attenuation correction: improving stress myocardial perfusion SPECT imaging using deep learning
Authors
Tomoe Hagio
Alexis Poitrasson-Rivière
Jonathan B. Moody
Jennifer M. Renaud
Liliana Arida-Moody
Ravi V. Shah
Edward P. Ficaro
Venkatesh L. Murthy
Publication date
21-03-2022
Publisher
Springer Berlin Heidelberg
Published in
European Journal of Nuclear Medicine and Molecular Imaging / Issue 9/2022
Print ISSN: 1619-7070
Electronic ISSN: 1619-7089
DOI
https://doi.org/10.1007/s00259-022-05735-7

Other articles of this Issue 9/2022

European Journal of Nuclear Medicine and Molecular Imaging 9/2022 Go to the issue