The Role of Deep Learning in Myocardial Perfusion Imaging for Diagnosis and Prognosis: A Systematic Review

Overview

Journal iScience

Publisher Cell Press

Date 2024 Dec 10

PMID 39654634

Authors

Xueping Hu

Han Zhang

Federico Caobelli

Yan Huang

Yuchen Li

Jiajia Zhang

Kuangyu Shi

Fei Yu

Affiliations

Soon will be listed here.

Abstract

The development of state-of-the-art algorithms for computer visualization has led to a growing interest in applying deep learning (DL) techniques to the field of medical imaging. DL-based algorithms have been extensively utilized in various aspects of cardiovascular imaging, and one notable area of focus is single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI), which is regarded as the gold standard for non-invasive diagnosis of myocardial ischemia. However, due to the complex decision-making process of DL based on convolutional neural networks (CNNs), the explainability of DL results has become a significant area of research, particularly in the field of medical imaging. To better harness the potential of DL and to be well prepared for the ongoing DL revolution in nuclear imaging, this review aims to summarize the recent applications of DL in MPI, with a specific emphasis on the methods in explainable DL for the diagnosis and prognosis of MPI. Furthermore, the challenges and potential directions for future research are also discussed.

References

Otaki Y, Singh A, Kavanagh P, Miller R, Parekh T, Tamarappoo B . Clinical Deployment of Explainable Artificial Intelligence of SPECT for Diagnosis of Coronary Artery Disease. JACC Cardiovasc Imaging. 2021; 15(6):1091-1102. PMC: 9020794. DOI: 10.1016/j.jcmg.2021.04.030. View

Vasilopoulou M, Asimakopoulou Z, Velissari J, Vicha A, Rizogianni M, Pusa S . Interventions about physical activity and diet and their impact on adolescent and young adult cancer survivors: a Prisma systematic review. Support Care Cancer. 2024; 32(6):342. PMC: 11090968. DOI: 10.1007/s00520-024-08516-0. View

Shi L, Onofrey J, Liu H, Liu Y, Liu C . Deep learning-based attenuation map generation for myocardial perfusion SPECT. Eur J Nucl Med Mol Imaging. 2020; 47(10):2383-2395. DOI: 10.1007/s00259-020-04746-6. View

Papandrianos N, Feleki A, Papageorgiou E, Martini C . Deep Learning-Based Automated Diagnosis for Coronary Artery Disease Using SPECT-MPI Images. J Clin Med. 2022; 11(13). PMC: 9267142. DOI: 10.3390/jcm11133918. View

Zhang H, Caobelli F, Che W, Huang Y, Zhang Y, Fan X . The prognostic value of CZT SPECT myocardial blood flow (MBF) quantification in patients with ischemia and no obstructive coronary artery disease (INOCA): a pilot study. Eur J Nucl Med Mol Imaging. 2023; 50(7):1940-1953. PMC: 10199834. DOI: 10.1007/s00259-023-06125-3. View

Teuho J, Schultz J, Klen R, Juarez-Orozco L, Knuuti J, Saraste A . Explainable deep-learning-based ischemia detection using hybrid O-15 HO perfusion positron emission tomography and computed tomography imaging with clinical data. J Nucl Cardiol. 2024; 38:101889. DOI: 10.1016/j.nuclcard.2024.101889. View

Yang J, Shi L, Wang R, Miller E, Sinusas A, Liu C . Direct Attenuation Correction Using Deep Learning for Cardiac SPECT: A Feasibility Study. J Nucl Med. 2021; 62(11):1645-1652. PMC: 8612332. DOI: 10.2967/jnumed.120.256396. View

Betancur J, Commandeur F, Motlagh M, Sharir T, Einstein A, Bokhari S . Deep Learning for Prediction of Obstructive Disease From Fast Myocardial Perfusion SPECT: A Multicenter Study. JACC Cardiovasc Imaging. 2018; 11(11):1654-1663. PMC: 6135711. DOI: 10.1016/j.jcmg.2018.01.020. View

Miller R, Hu L, Gransar H, Betancur J, Eisenberg E, Otaki Y . Transient ischaemic dilation and post-stress wall motion abnormality increase risk in patients with less than moderate ischaemia: analysis of the REFINE SPECT registry. Eur Heart J Cardiovasc Imaging. 2019; 21(5):567-575. PMC: 7167750. DOI: 10.1093/ehjci/jez172. View

10.

Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K . A guide to deep learning in healthcare. Nat Med. 2019; 25(1):24-29. DOI: 10.1038/s41591-018-0316-z. View

11.

Regitz-Zagrosek V, Gebhard C . Gender medicine: effects of sex and gender on cardiovascular disease manifestation and outcomes. Nat Rev Cardiol. 2022; 20(4):236-247. PMC: 9628527. DOI: 10.1038/s41569-022-00797-4. View

12.

Singh A, Miller R, Otaki Y, Kavanagh P, Hauser M, Tzolos E . Direct Risk Assessment From Myocardial Perfusion Imaging Using Explainable Deep Learning. JACC Cardiovasc Imaging. 2022; 16(2):209-220. PMC: 10980287. DOI: 10.1016/j.jcmg.2022.07.017. View

13.

Kaplan Berkaya S, Ak Sivrikoz I, Gunal S . Classification models for SPECT myocardial perfusion imaging. Comput Biol Med. 2020; 123:103893. DOI: 10.1016/j.compbiomed.2020.103893. View

14.

Chen X, Zhou B, Xie H, Shi L, Liu H, Holler W . Direct and indirect strategies of deep-learning-based attenuation correction for general purpose and dedicated cardiac SPECT. Eur J Nucl Med Mol Imaging. 2022; 49(9):3046-3060. PMC: 9253078. DOI: 10.1007/s00259-022-05718-8. View

15.

Wang J, Fan X, Qin S, Shi K, Zhang H, Yu F . Exploration of the efficacy of radiomics applied to left ventricular tomograms obtained from D-SPECT MPI for the auxiliary diagnosis of myocardial ischemia in CAD. Int J Cardiovasc Imaging. 2021; 38(2):465-472. DOI: 10.1007/s10554-021-02413-x. View

16.

Miller R, Kuronuma K, Singh A, Otaki Y, Hayes S, Chareonthaitawee P . Explainable Deep Learning Improves Physician Interpretation of Myocardial Perfusion Imaging. J Nucl Med. 2022; 63(11):1768-1774. PMC: 9635672. DOI: 10.2967/jnumed.121.263686. View

17.

Miller R, Shanbhag A, Killekar A, Lemley M, Bednarski B, Van Kriekinge S . AI-derived epicardial fat measurements improve cardiovascular risk prediction from myocardial perfusion imaging. NPJ Digit Med. 2024; 7(1):24. PMC: 10838293. DOI: 10.1038/s41746-024-01020-z. View

18.

Kusumoto D, Akiyama T, Hashimoto M, Iwabuchi Y, Katsuki T, Kimura M . A deep learning-based automated diagnosis system for SPECT myocardial perfusion imaging. Sci Rep. 2024; 14(1):13583. PMC: 11169468. DOI: 10.1038/s41598-024-64445-2. View

19.

Rahman M, Yu Z, Laforest R, Abbey C, Siegel B, Jha A . DEMIST: A Deep-Learning-Based Detection-Task-Specific Denoising Approach for Myocardial Perfusion SPECT. IEEE Trans Radiat Plasma Med Sci. 2024; 8(4):439-450. PMC: 11101197. DOI: 10.1109/trpms.2024.3379215. View

20.

Slomka P, Xu Y, Berman D, Germano G . Quantitative analysis of perfusion studies: strengths and pitfalls. J Nucl Cardiol. 2012; 19(2):338-46. PMC: 3412547. DOI: 10.1007/s12350-011-9509-2. View