Explainable deep-learning-based ischemia detection using hybrid O-15 H2O perfusion positron emission tomography and computed tomography imaging with clinical data.

BACKGROUND: We developed an explainable deep-learning (DL)-based classifier to identify flow-limiting coronary artery disease (CAD) by O-15 H2O perfusion positron emission tomography computed tomography (PET/CT) and coronary CT angiography (CTA) imaging. The classifier uses polar map images with numerical data and visualizes data findings. METHODS: A DLmodel was implemented and evaluated on 138 individuals, consisting of a combined image-and data-based classifier considering 35 clinical, CTA, and PET variables. Data from invasive coronary angiography were used as reference. Performance was evaluated with clinical classification using accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score (F1S), sensitivity (SEN), specificity (SPE), precision (PRE), net benefit, and Cohen's Kappa. Statistical testing was conducted using McNemar's test. RESULTS: The DL model had a median ACC = 0.8478, AUC = 0.8481, F1S = 0.8293, SEN = 0.8500, SPE = 0.8846, and PRE = 0.8500. Improved detection of true-positive and false-negative cases, increased net benefit in thresholds up to 34%, and comparable Cohen's kappa was seen, reaching similar performance to clinical reading. Statistical testing revealed no significant differences between DL model and clinical reading. CONCLUSIONS: The combined DL model is a feasible and an effective method in detection of CAD, allowing to highlight important data findings individually in interpretable manner.

Hybridizing machine learning in survival analysis of cardiac PET/CT imaging.

BACKGROUND: Machine Learning (ML) allows integration of the numerous variables delivered by cardiac PET/CT, while traditional survival analysis can provide explainable prognostic estimates from a restricted number of input variables. We implemented a hybrid ML-and-survival analysis of multimodal PET/CT data to identify patients who developed myocardial infarction (MI) or death in long-term follow up. METHODS: Data from 739 intermediate risk patients who underwent coronary CT and selectively stress 15O-water-PET perfusion were analyzed for the occurrence of MI and all-cause mortality. Images were evaluated segmentally for atherosclerosis and absolute myocardial perfusion through 75 variables that were integrated through ML into an ML-CCTA and an ML-PET score. These scores were then modeled along with clinical variables through Cox regression. This hybridized model was compared against an expert interpretation-based and a calcium score-based model. RESULTS: Compared with expert- and calcium score-based models, the hybridized ML-survival model showed the highest performance (CI .81 vs .71 and .64). The strongest predictor for outcomes was the ML-CCTA score. CONCLUSION: Prognostic modeling of PET/CT data for the long-term occurrence of adverse events may be improved through ML imaging score integration and subsequent traditional survival analysis with clinical variables. This hybridization of methods offers an alternative to traditional survival modeling of conventional expert image scoring and interpretation.

Genome-Wide Association Study and Identification of a Protective Missense Variant on Lipoprotein(a) Concentration: Protective Missense Variant on Lipoprotein(a) Concentration-Brief Report.

[Figure: see text].

Multi-task Deep Learning of Myocardial Blood Flow and Cardiovascular Risk Traits from PET Myocardial Perfusion Imaging.

BACKGROUND: Advanced cardiac imaging with positron emission tomography (PET) is a powerful tool for the evaluation of known or suspected cardiovascular disease. Deep learning (DL) offers the possibility to abstract highly complex patterns to optimize classification and prediction tasks. METHODS AND RESULTS: We utilized DL models with a multi-task learning approach to identify an impaired myocardial flow reserve (MFR <2.0 ml/g/min) as well as to classify cardiovascular risk traits (factors), namely sex, diabetes, arterial hypertension, dyslipidemia and smoking at the individual-patient level from PET myocardial perfusion polar maps using transfer learning. Performance was assessed on a hold-out test set through the area under receiver operating curve (AUC). DL achieved the highest AUC of 0.94 [0.87-0.98] in classifying an impaired MFR in reserve perfusion polar maps. Fine-tuned DL for the classification of cardiovascular risk factors yielded the highest performance in the identification of sex from stress polar maps (AUC = 0.81 [0.73, 0.88]). Identification of smoking achieved an AUC = 0.71 [0.58, 0.85] from the analysis of rest polar maps. The identification of dyslipidemia and arterial hypertension showed poor performance and was not statistically significant. CONCLUSION: Multi-task DL for the evaluation of quantitative PET myocardial perfusion polar maps is able to identify an impaired MFR as well as cardiovascular risk traits such as sex, smoking and possibly diabetes at the individual-patient level.

Artificial Intelligence to Improve Risk Prediction with Nuclear Cardiac Studies.

PURPOSE OF REVIEW: As machine learning-based artificial intelligence (AI) continues to revolutionize the way in which we analyze data, the field of nuclear cardiology provides fertile ground for the implementation of these complex analytics. This review summarizes and discusses the principles regarding nuclear cardiology techniques and AI, and the current evidence regarding its performance and contribution to the improvement of risk prediction in cardiovascular disease. There is a growing body of evidence on the experimentation with and implementation of machine learning-based AI on nuclear cardiology studies both concerning SPECT and PET technology for the improvement of risk-of-disease (classification of disease) and risk-of-events (prediction of adverse events) estimations. These publications still report objective divergence in methods either utilizing statistical machine learning approaches or deep learning with varying architectures, dataset sizes, and performance. Recent efforts have been placed into bringing standardization and quality to the experimentation and application of machine learning-based AI in cardiovascular imaging to generate standards in data harmonization and analysis through AI. Machine learning-based AI offers the possibility to improve risk evaluation in cardiovascular disease through its implementation on cardiac nuclear studies. AI in improving risk evaluation in nuclear cardiology. * Based on the 2019 ESC guidelines.

Validation of the European Society of Cardiology pre-test probability model for obstructive coronary artery disease.

AIMS: Estimation of pre-test probability (PTP) of disease in patients with suspected coronary artery disease (CAD) is a common challenge. Due to decreasing prevalence of obstructive CAD in patients referred for diagnostic testing, the European Society of Cardiology suggested a new PTP (2019-ESC-PTP) model. The aim of this study was to validate that model. METHODS AND RESULTS: Symptomatic patients referred for coronary computed tomography angiography (CTA) due to suspected CAD in a geographical uptake area of 3.3 million inhabitants were included. The reference standard was a combined endpoint of CTA and invasive coronary angiography (ICA) with obstructive CAD defined at ICA as a ≥50% diameter stenosis or fractional flow reserve ≤0.80 when performed. The 2019-ESC-PTP, 2013-ESC-PTP, and CAD Consortium basic PTP scores were calculated based on age, sex, and symptoms. Of the 42 328 identified patients, coronary stenosis was detected in 8.8% using the combined endpoint. The 2019-ESC-PTP and CAD Consortium basic scores classified substantially more patients into the low PTP groups (PTP < 15%) than did the 2013-ESC-PTP (64% and 65% vs. 16%, P < 0.001). Using the combined endpoint as reference, calibration of the 2019-ESC-PTP model was superior to the 2013-ESC-PTP and CAD Consortium basic score. CONCLUSION: The new 2019-ESC-PTP model is well calibrated and superior to the previously recommended models in predicting obstructive stenosis detected by a combined endpoint of CTA and ICA.

Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT.

In daily clinical practice, clinicians integrate available data to ascertain the diagnostic and prognostic probability of a disease or clinical outcome for their patients. For patients with suspected or known cardiovascular disease, several anatomical and functional imaging techniques are commonly performed to aid this endeavor, including coronary computed tomography angiography (CCTA) and nuclear cardiology imaging. Continuous improvement in positron emission tomography (PET), single-photon emission computed tomography (SPECT), and CT hardware and software has resulted in improved diagnostic performance and wide implementation of these imaging techniques in daily clinical practice. However, the human ability to interpret, quantify, and integrate these data sets is limited. The identification of novel markers and application of machine learning (ML) algorithms, including deep learning (DL) to cardiovascular imaging techniques will further improve diagnosis and prognostication for patients with cardiovascular diseases. The goal of this position paper of the European Association of Nuclear Medicine (EANM) and the European Association of Cardiovascular Imaging (EACVI) is to provide an overview of the general concepts behind modern machine learning-based artificial intelligence, highlights currently prefered methods, practices, and computational models, and proposes new strategies to support the clinical application of ML in the field of cardiovascular imaging using nuclear cardiology (hybrid) and CT techniques.

Ventricular synchrony is not significantly determined by absolute myocardial perfusion in patients with chronic heart failure: A 13N-ammonia PET study.

BACKGROUND: It is thought that heart failure (HF) patients may benefit from the evaluation of mechanical (dys)synchrony, and an independent inverse relationship between myocardial perfusion and ventricular synchrony has been suggested. We explore the relationship between quantitative myocardial perfusion and synchrony parameters when accounting for the presence and extent of fixed perfusion defects in patients with chronic HF. METHODS: We studied 98 patients with chronic HF who underwent rest and stress Nitrogen-13 ammonia PET. Multivariate analyses of covariance were performed to determine relevant predictors of synchrony (measured as bandwidth, standard deviation, and entropy). RESULTS: In our population, there were 43 (44%) women and 55 men with a mean age of 71 ± 9.6 years. The SRS was the strongest independent predictor of mechanical synchrony variables (p < .01), among other considered predictors including: age, sex, body mass index, smoking, diabetes mellitus, dyslipidemia, hypertension, rest myocardial blood flow (MBF), and myocardial perfusion reserve (MPR). Results were similar when considering stress MBF instead of MPR. CONCLUSIONS: The existence and extent of fixed perfusion defects, but not the quantitative PET myocardial perfusion parameters (sMBF and MPR), constitute a significant independent predictor of ventricular mechanical synchrony in patients with chronic HF.

Machine learning in the integration of simple variables for identifying patients with myocardial ischemia.

BACKGROUND: A significant number of variables are obtained when characterizing patients suspected with myocardial ischemia or at risk of MACE. Guidelines typically use a handful of them to support further workup or therapeutic decisions. However, it is likely that the numerous available predictors maintain intrinsic complex interrelations. Machine learning (ML) offers the possibility to elucidate complex patterns within data to optimize individual patient classification. We evaluated the feasibility and performance of ML in utilizing simple accessible clinical and functional variables for the identification of patients with ischemia or an elevated risk of MACE as determined through quantitative PET myocardial perfusion reserve (MPR). METHODS: 1,234 patients referred to Nitrogen-13 ammonia PET were analyzed. Demographic (4), clinical (8), and functional variables (9) were retrieved and input into a cross-validated ML workflow consisting of feature selection and modeling. Two PET-defined outcome variables were operationalized: (1) any myocardial ischemia (regional MPR < 2.0) and (2) an elevated risk of MACE (global MPR < 2.0). ROC curves were used to evaluate ML performance. RESULTS: 16 features were included for boosted ensemble ML. ML achieved an AUC of 0.72 and 0.71 in identifying patients with myocardial ischemia and with an elevated risk of MACE, respectively. ML performance was superior to logistic regression when the latter used the ESC guidelines risk models variables for both PET-defined labels (P < .001 and P = .01, respectively). CONCLUSIONS: ML is feasible and applicable in the evaluation and utilization of simple and accessible predictors for the identification of patients who will present myocardial ischemia and an elevated risk of MACE in quantitative PET imaging.

Software reproducibility of myocardial blood flow and flow reserve quantification in ischemic heart disease: A 13N-ammonia PET study.

BACKGROUND: We explored agreement in the quantification of myocardial perfusion by cross-comparison of implemented software packages (SPs) in three distinguishable patient profile populations. METHODS: We studied 91 scans of patients divided into 3 subgroups based on their semi-quantitative perfusion findings: patients with normal perfusion, with reversible perfusion defects, and with fixed perfusion defects. Rest myocardial blood flow (MBF), stress MBF, and myocardial flow reserve (MFR) were obtained with QPET, SyngoMBF, and Carimas. Agreement between SPs was considered adequate when a pairwise standardized difference was found to be < 0.20 and its corresponding intraclass correlation coefficient was ≥ 0.75. RESULTS: In patients with normal perfusion, two out of three comparisons of global stress MBF quantifications were outside the limits of agreement. In ischemic patients, all comparisons of global stress MBF and MFR were outside the limits of established agreement. In patients with fixed perfusion defects, all SP comparisons of perfusion quantifications were within the limit of agreement. Regionally, agreement of these perfusion estimates was mostly found for the left anterior descending artery vascular territory. CONCLUSION: Reversible defects demonstrated the worst agreement in global stress MBF and MFR and discrepancies showed to be regional dependent. Reproducibility between SPs should not be assumed.

Comparison of the amount and patterns of late enhancement in Chagas disease according to the presence and type of ventricular tachycardia.

BACKGROUND: Ventricular tachycardia (VT) is one of the main predictors of mortality in Chagas cardiomyopathy (CC). Although the substrate of sustained and nonsustained-VT (NS-VT) seems to be the same, little is known about the distribution of late enhancement (LE). Our aim was to compare the clinical findings and the amount and patterns of LE in Chagas disease according to the presence and type of VT. METHODS AND RESULTS: Magnetic resonance imaging was performed in 54 Chagas seropositive patients: 8 indeterminate and 46 with CC of whom 15 were without VT, 13 with NS-VT, and 18 with sustained-VT (S-VT). There were 31 males (57%), mean age was 55.9 ± 12.2 years. LE was found in 87% of all patients and in 50%, 80%, and 100% of the indeterminate, without VT and VT groups, respectively. The percentage of LE increased progressively in the indeterminate, CC without VT, and CC with VT groups; without a significant difference between NS-VT and S-VT (0.93%, 15.2%, 23.2%, and 21.4%, respectively). The amount of LE increased with the functional class. LE in the basal and mid lateral wall was more frequent in VT, without difference between S-VT and NS-VT. The only predictor of VT was the percentage of LE, odds ratio (OR), 6.2; (95% confidence interval [CI], 3.7-28.4; P = .01) with a cutoff of Odds Ratio 17.1%. CONCLUSIONS: The amount of LE increases in relation to the clinical stage of the disease and its functional class in Chagas seropositive patients. The amount of LE was the main predictor of VT, without difference between S-VT and NS-VT.

Phase analysis of gated PET in the evaluation of mechanical ventricular synchrony: A narrative overview.

Noninvasive imaging modalities offer the possibility to dynamically evaluate cardiac motion during the cardiac cycle by means of ECG-gated acquisitions. Such motion characterization along with orientation, segmentation preprocessing, and ultimately, phase analysis, can provide quantitative estimates of ventricular mechanical synchrony. Current evidence on the role of mechanical synchrony evaluation is mainly available for echocardiography and gated single-photon emission computed tomography, but less is known about the utilization of gated positron emission tomography (PET). Although data available are sparse, there is indication that mechanical synchrony evaluation can be of diagnostic and prognostic values in patients with known or suspected coronary artery disease-related myocardial ischemia, prediction of response to cardiac resynchronization therapy, and estimation of risk for adverse cardiac events in patients' heart failure. As such, the evaluation of mechanical ventricular synchrony through phase analysis of gated acquisitions represents a value addition to modern cardiac PET imaging modality, which warrants further research and development in the evaluation of patients with cardiovascular disease.

The performance of non-invasive tests to rule-in and rule-out significant coronary artery stenosis in patients with stable angina: a meta-analysis focused on post-test disease probability.

Aims: To determine the ranges of pre-test probability (PTP) of coronary artery disease (CAD) in which stress electrocardiogram (ECG), stress echocardiography, coronary computed tomography angiography (CCTA), single-photon emission computed tomography (SPECT), positron emission tomography (PET), and cardiac magnetic resonance (CMR) can reclassify patients into a post-test probability that defines (>85%) or excludes (<15%) anatomically (defined by visual evaluation of invasive coronary angiography [ICA]) and functionally (defined by a fractional flow reserve [FFR] ≤0.8) significant CAD. Methods and results: A broad search in electronic databases until August 2017 was performed. Studies on the aforementioned techniques in >100 patients with stable CAD that utilized either ICA or ICA with FFR measurement as reference, were included. Study-level data was pooled using a hierarchical bivariate random-effects model and likelihood ratios were obtained for each technique. The PTP ranges for each technique to rule-in or rule-out significant CAD were defined. A total of 28 664 patients from 132 studies that used ICA as reference and 4131 from 23 studies using FFR, were analysed. Stress ECG can rule-in and rule-out anatomically significant CAD only when PTP is ≥80% (76-83) and ≤19% (15-25), respectively. Coronary computed tomography angiography is able to rule-in anatomic CAD at a PTP ≥58% (45-70) and rule-out at a PTP ≤80% (65-94). The corresponding PTP values for functionally significant CAD were ≥75% (67-83) and ≤57% (40-72) for CCTA, and ≥71% (59-81) and ≤27 (24-31) for ICA, demonstrating poorer performance of anatomic imaging against FFR. In contrast, functional imaging techniques (PET, stress CMR, and SPECT) are able to rule-in functionally significant CAD when PTP is ≥46-59% and rule-out when PTP is ≤34-57%. Conclusion: The various diagnostic modalities have different optimal performance ranges for the detection of anatomically and functionally significant CAD. Stress ECG appears to have very limited diagnostic power. The selection of a diagnostic technique for any given patient to rule-in or rule-out CAD should be based on the optimal PTP range for each test and on the assumed reference standard.

Stress myocardial blood flow correlates with ventricular function and synchrony better than myocardial perfusion reserve: A Nitrogen-13 ammonia PET study.

BACKGROUND: Cardiac PET quantifies stress myocardial blood flow (MBF) and perfusion reserve (MPR), while ECG-gated datasets can measure components of ventricular function simultaneously. Stress MBF seems to outperform MPR in the detection of significant CAD. However, it is uncertain which perfusion measurement is more related to ventricular function. We hypothesized that stress MBF correlates with ventricular function better than MPR in patients studied for suspected myocardial ischemia. METHODS: We studied 248 patients referred to a rest and adenosine-stress Nitrogen-13 ammonia PET. We performed a multivariate analysis using systolic function (left ventricular ejection fraction, LVEF), diastolic function (mean filling rate in diastole, MFR/3), and synchrony (Entropy) as the outcome variables, and stress MBF, MPR, and relevant covariates as the predictors. Secondarily, we repeated the analysis for the subgroup of patients with and without a previous myocardial infarction (MI). RESULTS: 166 male and 82 female patients (mean age 63 ± 11 and 67 ± 11 year, respectively) were included. 60% of the patients presented hypertension, 57% dyslipidemia, 21% type 2 diabetes mellitus, 45% smoking, and 34.7% a previous MI. Mean stress MBF was 1.99 ± 0.75 mL/g/min, MPR = 2.55 ± 0.89, LVEF = 61.6 ± 15%, MFR/3 = 1.12 ± 0.38 EDV/s, and Entropy = 45.6 ± 11.3%. There was a significant correlation between stress MBF (P < .001) and ventricular function. This was stronger than the one for MPR (P = .063). Sex, age, diabetes, and extent of previous MI were also significant predictors. Results were similar for the analyses of the 2 subgroups. CONCLUSION: Stress MBF is better correlated with ventricular function than MPR, as evaluated by Nitrogen-13 ammonia PET, independently from other relevant cardiovascular risk factors and clinical covariates. This relationship between coronary vasodilatory capacity and ventricular function is sustained across groups with and without a previous MI.

Type 2 diabetes mellitus correlates with systolic function during myocardial stress perfusion scanning with Nitrogen-13 ammonia PET.

BACKGROUND: The influence of type 2 diabetes mellitus (DM2) on systolic function is partially determined by the coronary vasodilator function, nevertheless, an independent effect is suspected. We evaluated the relationship between DM2 and systolic function considering PET quantitative myocardial perfusion. METHODS: We analyzed 585 patients without a previous myocardial infarction referred to a rest and adenosine stress Nitrogen-13 ammonia PET. A bootstrapped multiple linear regression analysis was performed using DM2, stress myocardial blood flow (sMBF), myocardial perfusion reserve (MPR), and clinical risk factors as predictors and LVEF as the outcome variable; an interaction term was additionally investigated. RESULTS: Two hundred and ninety male and 295 female patients (mean age 65.3 ± 9.9 and 67.4 ± 10 years, respectively) were included. 57.1% presented hypertension, 16% smoking, 37.6% hypercholesterolemia, 33.8% family history for CAD, and 15.2% DM2. The mean MPR was 2.13 ± 0.48 and 2.21 ± 0.60, mean sMBF was 2.01 ± 0.51 and 2.15 ± 0.54, and mean LVEF was 63% ± 10.4 and 67% ± 10.1 for diabetics and non-diabetics, respectively. A significant relation was detected for sMBF (B = 5.830 95% CI [3.505, 9.549], P = .001) and DM2 (B = -2.599 95% CI [-5.125, -0.119], P = .03) with LVEF. The interaction (DM2 × sMBF) yielded no significance (P = .512). CONCLUSION: DM2 influences PET-measured systolic function in patients without previous myocardial infarction independently from myocardial perfusion parameters. Our study supports the importance of DM2 as an independent risk factor for deteriorating systolic function.

[18F]-Sodium fluoride uptake in Takayasu arteritis.

BACKGROUND: While 18F-fluorodeoxyglucose and 18F-sodium fluoride with positron emission tomography relate with inflammation and calcification, their role in the assessment of patients with Takayasu arteritis has not yet been studied. METHODS: We present 5 patients with suspected active metabolic disease who underwent PET with 18F-fluorodeoxyglucose and 18F-sodium fluoride in order to explore the locations and correlations of 18F-fluorodeoxyglucose and 18F-sodium fluoride uptakes. Diagnosis of metabolic active disease was based on 18F-fluorodeoxyglucose uptake. RESULTS: We studied 3 female patients and 2 male patients. Median age was 29 years (min: 19 max: 63). In areas with atherosclerotic plaques, we found a negative correlation between 18F-sodium fluoride and 18F-fluorodeoxyglucose uptakes (r = -0.78) (P = .001). Meanwhile, in areas with only metabolic active disease, we found a positive correlation between 18F-sodium fluoride and 18F-fluorodeoxyglucose uptakes (r = 0.94) (P = .019). CONCLUSIONS: In Takayasu arteritis, 18F-sodium fluoride uptake can document different stages of metabolic disease, even in the absence of active metabolic disease or symptoms.

Myocardial perfusion reserve in spared myocardium: correlation with infarct size and left ventricular ejection fraction.

PURPOSE: Left ventricular ejection fraction (LVEF) after myocardial infarction is considered to be determined by the size of the infarction and residual function of the spared myocardium. Myocardial perfusion reserve (MPR) has been shown to be a strong prognostic factor in patients with ischaemic heart failure, even stronger than LVEF. In the present study, the interrelationship between MPR, LVEF and infarct size was investigated. METHODS: In total, 102 patients with a prior history of myocardial infarction were included. All underwent rest and stress (13)N-ammonia and gated (18)F-fluorodeoxyglucose ((18)F-FDG) positron emission tomography (PET) for evaluation of myocardial ischaemia and viability. FDG polar maps were used to determine the size of the infarction. The LVEF was obtained by gated (18)F-FDG PET or another available method within 3 months of the PET scan. MPR was obtained per segment in the spared myocardium. RESULTS: The mean age of the subjects was 68 ± 12 years. Global MPR was 1.63 ± 0.51. The mean LVEF was 36 ± 10 % and mean infarct size 23.72 ± 14.8 %. A linear regression model was applied for the analysis considering the LVEF as a dependent variable. All risk factors, mean stress flow, infarct size and MPR were entered as variables. The infarct size (p < 0.001) and MPR (p = 0.04) reached statistical significance. In a multivariate model MPR had a stronger correlation with LVEF than infarct size. CONCLUSION: In patients with a prior history of myocardial infarction, LVEF is not just related to infarct size but also to MPR in the spared myocardium.

Synthetic Attenuation Correction Maps for SPECT Imaging Using Deep Learning: A Study on Myocardial Perfusion Imaging.

(1) Background: The CT-based attenuation correction of SPECT images is essential for obtaining accurate quantitative images in cardiovascular imaging. However, there are still many SPECT cameras without associated CT scanners throughout the world, especially in developing countries. Performing additional CT scans implies troublesome planning logistics and larger radiation doses for patients, making it a suboptimal solution. Deep learning (DL) offers a revolutionary way to generate complementary images for individual patients at a large scale. Hence, we aimed to generate linear attenuation coefficient maps from SPECT emission images reconstructed without attenuation correction using deep learning. (2) Methods: A total of 384 SPECT myocardial perfusion studies that used 99mTc-sestamibi were included. A DL model based on a 2D U-Net architecture was trained using information from 312 patients. The quality of the generated synthetic attenuation correction maps (ACMs) and reconstructed emission values were evaluated using three metrics and compared to standard-of-care data using Bland-Altman plots. Finally, a quantitative evaluation of myocardial uptake was performed, followed by a semi-quantitative evaluation of myocardial perfusion. (3) Results: In a test set of 66 test patients, the ACM quality metrics were MSSIM = 0.97 ± 0.001 and NMAE = 3.08 ± 1.26 (%), and the reconstructed emission quality metrics were MSSIM = 0.99 ± 0.003 and NMAE = 0.23 ± 0.13 (%). The 95% limits of agreement (LoAs) at the voxel level for reconstructed SPECT images were: [-9.04; 9.00]%, and for the segment level, they were [-11; 10]%. The 95% LoAs for the Summed Stress Score values between the images reconstructed were [-2.8, 3.0]. When global perfusion scores were assessed, only 2 out of 66 patients showed changes in perfusion categories. (4) Conclusion: Deep learning can generate accurate attenuation correction maps from non-attenuation-corrected cardiac SPECT images. These high-quality attenuation maps are suitable for attenuation correction in myocardial perfusion SPECT imaging and could obviate the need for additional imaging in standalone SPECT scanners.