Predicting mortality from AI cardiac volumes mass and coronary calcium on chest computed tomography.

Chest computed tomography is one of the most common diagnostic tests, with 15 million scans performed annually in the United States. Coronary calcium can be visualized on these scans, but other measures of cardiac risk such as atrial and ventricular volumes have classically required administration of contrast. Here we show that a fully automated pipeline, incorporating two artificial intelligence models, automatically quantifies coronary calcium, left atrial volume, left ventricular mass, and other cardiac chamber volumes in 29,687 patients from three cohorts. The model processes chamber volumes and coronary artery calcium with an end-to-end time of ~18 s, while failing to segment only 0.1% of cases. Coronary calcium, left atrial volume, and left ventricular mass index are independently associated with all-cause and cardiovascular mortality and significantly improve risk classification compared to identification of abnormalities by a radiologist. This automated approach can be integrated into clinical workflows to improve identification of abnormalities and risk stratification, allowing physicians to improve clinical decision-making.

AI-derived epicardial fat measurements improve cardiovascular risk prediction from myocardial perfusion imaging.

Epicardial adipose tissue (EAT) volume and attenuation are associated with cardiovascular risk, but manual annotation is time-consuming. We evaluated whether automated deep learning-based EAT measurements from ungated computed tomography (CT) are associated with death or myocardial infarction (MI). We included 8781 patients from 4 sites without known coronary artery disease who underwent hybrid myocardial perfusion imaging. Of those, 500 patients from one site were used for model training and validation, with the remaining patients held out for testing (n = 3511 internal testing, n = 4770 external testing). We modified an existing deep learning model to first identify the cardiac silhouette, then automatically segment EAT based on attenuation thresholds. Deep learning EAT measurements were obtained in <2 s compared to 15 min for expert annotations. There was excellent agreement between EAT attenuation (Spearman correlation 0.90 internal, 0.82 external) and volume (Spearman correlation 0.90 internal, 0.91 external) by deep learning and expert segmentation in all 3 sites (Spearman correlation 0.90-0.98). During median follow-up of 2.7 years (IQR 1.6-4.9), 565 patients experienced death or MI. Elevated EAT volume and attenuation were independently associated with an increased risk of death or MI after adjustment for relevant confounders. Deep learning can automatically measure EAT volume and attenuation from low-dose, ungated CT with excellent correlation with expert annotations, but in a fraction of the time. EAT measurements offer additional prognostic insights within the context of hybrid perfusion imaging.

Automated vessel specific coronary artery calcification quantification with deep learning in a large multi-center registry.

AIMS: Vessel specific coronary artery calcification (CAC) is additive to global CAC for prognostic assessment. We assessed accuracy and prognostic implications of vessel-specific automated deep learning (DL) CAC analysis on electrocardiogram gated and attenuation correction computed tomography (CT) in a large multicenter registry. METHODS AND RESULTS: Vessel-specific CAC was assessed in the left main/left anterior descending (LM/LAD), left circumflex (LCX) and right coronary artery (RCA) using a DL model trained on 3000 gated CT and tested on 2094 gated CT and 5969 non-gated attenuation correction CT. Vessel-specific agreement was assessed with linear weighted Cohen's Kappa for CAC zero, 1-100, 101-400 and >400 Agatston units (AU). Risk of major adverse cardiovascular events (MACE) was assessed during 2.4±1.4 years follow-up, with hazard ratios (HR) and 95% confidence intervals (CI). There was strong to excellent agreement between DL and expert ground truth for CAC in LM/LAD, LCX and RCA on gated CT [0.90 (95% CI 0.89 to 0.92); 0.70 (0.68 to 0.73); 0.79 (0.77 to 0.81)] and attenuation correction CT [(0.78 (0.77 to 0.80); 0.60 (0.58 to 0.62); 0.70 (0.68 to 0.71)]. MACE occurred in 242 (12%) undergoing gated CT and 841(14%) of undergoing attenuation correction CT. LM/LAD CAC >400 AU was associated with the highest risk of MACE on gated (HR 12.0, 95% CI 7.96, 18.0, p<0.001) and attenuation correction CT (HR 4.21, 95% CI 3.48, 5.08, p<0.001). CONCLUSION: Vessel-specific CAC assessment with DL can be performed accurately and rapidly on gated CT and attenuation correction CT and provides important prognostic information.

Downward myocardial creep during stress PET imaging is inversely associated with mortality.

PURPOSE: The myocardial creep is a phenomenon in which the heart moves from its original position during stress-dynamic PET myocardial perfusion imaging (MPI) that can confound myocardial blood flow measurements. Therefore, myocardial motion correction is important to obtain reliable myocardial flow quantification. However, the clinical importance of the magnitude of myocardial creep has not been explored. We aimed to explore the prognostic value of myocardial creep quantified by an automated motion correction algorithm beyond traditional PET-MPI imaging variables. METHODS: Consecutive patients undergoing regadenoson rest-stress [82Rb]Cl PET-MPI were included. A newly developed 3D motion correction algorithm quantified myocardial creep, the maximum motion at stress during the first pass (60 s), in each direction. All-cause mortality (ACM) served as the primary endpoint. RESULTS: A total of 4,276 patients (median age 71 years; 60% male) were analyzed, and 1,007 ACM events were documented during a 5-year median follow-up. Processing time for automatic motion correction was < 12 s per patient. Myocardial creep in the superior to inferior (downward) direction was greater than the other directions (median, 4.2 mm vs. 1.3-1.7 mm). Annual mortality rates adjusted for age and sex were reduced with a larger downward creep, with a 4.2-fold ratio between the first (0 mm motion) and 10th decile (11 mm motion) (mortality, 7.9% vs. 1.9%/year). Downward creep was associated with lower ACM after full adjustment for clinical and imaging parameters (adjusted hazard ratio, 0.93; 95%CI, 0.91-0.95; p < 0.001). Adding downward creep to the standard PET-MPI imaging model significantly improved ACM prediction (area under the receiver operating characteristics curve, 0.790 vs. 0.775; p < 0.001), but other directions did not (p > 0.5). CONCLUSIONS: Downward myocardial creep during regadenoson stress carries additional information for the prediction of ACM beyond conventional flow and perfusion PET-MPI. This novel imaging biomarker is quantified automatically and rapidly from stress dynamic PET-MPI.

Automated Motion Correction for Myocardial Blood Flow Measurements and Diagnostic Performance of 82Rb PET Myocardial Perfusion Imaging.

Motion correction (MC) affects myocardial blood flow (MBF) measurements in 82Rb PET myocardial perfusion imaging (MPI); however, frame-by-frame manual MC of dynamic frames is time-consuming. This study aims to develop an automated MC algorithm for time-activity curves used in compartmental modeling and compare the predictive value of MBF with and without automated MC for significant coronary artery disease (CAD). Methods: In total, 565 patients who underwent PET-MPI were considered. Patients without angiographic findings were split into training (n = 112) and validation (n = 112) groups. The automated MC algorithm used simplex iterative optimization of a count-based cost function and was developed using the training group. MBF measurements with automated MC were compared with those with manual MC in the validation group. In a separate cohort, 341 patients who underwent PET-MPI and invasive coronary angiography were enrolled in the angiographic group. The predictive performance in patients with significant CAD (≥70% stenosis) was compared between MBF measurements with and without automated MC. Results: In the validation group (n = 112), MBF measurements with automated and manual MC showed strong correlations (r = 0.98 for stress MBF and r = 0.99 for rest MBF). The automatic MC took less time than the manual MC (<12 s vs. 10 min per case). In the angiographic group (n = 341), MBF measurements with automated MC decreased significantly compared with those without (stress MBF, 2.16 vs. 2.26 mL/g/min; rest MBF, 1.12 vs. 1.14 mL/g/min; MFR, 2.02 vs. 2.10; all P < 0.05). The area under the curve (AUC) for the detection of significant CAD by stress MBF with automated MC was higher than that without (AUC, 95% CI, 0.76 [0.71-0.80] vs. 0.73 [0.68-0.78]; P < 0.05). The addition of stress MBF with automated MC to the model with ischemic total perfusion deficit showed higher diagnostic performance for detection of significant CAD (AUC, 95% CI, 0.82 [0.77-0.86] vs. 0.78 [0.74-0.83]; P = 0.022), but the addition of stress MBF without MC to the model with ischemic total perfusion deficit did not reach significance (AUC, 95% CI, 0.81 [0.76-0.85] vs. 0.78 [0.74-0.83]; P = 0.067). Conclusion: Automated MC on 82Rb PET-MPI can be performed rapidly with excellent agreement with experienced operators. Stress MBF with automated MC showed significantly higher diagnostic performance than without MC.

Incremental prognostic value of stress phase entropy over standard PET myocardial perfusion imaging variables.

PURPOSE: Phase analysis can assess left ventricular dyssynchrony. The independent prognostic value of phase variables over positron emission tomography myocardial perfusion imaging (PET-MPI) variables including myocardial flow reserve (MFR) has not been studied. The aim of this study was to explore the prognostic value of phase variables for predicting mortality over standard PET-MPI variables. METHODS: Consecutive patients who underwent pharmacological stress-rest 82Rb PET study were enrolled. All PET-MPI variables including phase variables (phase entropy, phase bandwidth, and phase standard deviation) were automatically obtained by QPET software (Cedars-Sinai, Los Angeles, CA). Cox proportional hazard analyses were used to assess associations with all-cause mortality (ACM). RESULTS: In a total of 3963 patients (median age 71 years; 57% male), 923 patients (23%) died during a median follow-up of 5 years. Annualized mortality rates increased with stress phase entropy, with a 4.6-fold difference between the lowest and highest decile groups of entropy (2.6 vs. 12.0%/year). Abnormal stress phase entropy (optimal cutoff value, 43.8%) stratified ACM risk in patients with normal and impaired MFR (both p < 0.001). Among three phase variables, only stress phase entropy was significantly associated with ACM after the adjustment of standard clinical and PET-MPI variables including MFR and stress-rest change of phase variables, whether modeled as binary variables (adjusted hazard ratio, 1.44 for abnormal entropy [> 43.8%]; 95%CI, 1.18-1.75; p < 0.001) or continuous variables (adjusted hazard ratio, 1.05 per 5% increase; 95%CI, 1.01-1.10; p = 0.030). The addition of stress phase entropy to the standard PET-MPI variables significantly improved the discriminatory power for ACM prediction (p < 0.001), but the other phase variables did not (p > 0.1). CONCLUSION: Stress phase entropy is independently and incrementally associated with ACM beyond standard PET-MPI variables including MFR. Phase entropy can be obtained automatically and included in clinical reporting of PET-MPI studies to improve patient risk prediction.

Usefulness of phase analysis on ECG gated single photon emission computed tomography myocardial perfusion imaging.

Electrocardiogram (ECG)-gated single photon emission computed tomography myocardial perfusion imaging (GSPECT-MPI) is widely used for assessing coronary artery disease. Phase analysis on GSPECT-MPI can assess left ventricular mechanical dyssynchrony quantitatively on standard GSPECT-MPI alongside myocardial perfusion and function assessment. It has been shown that phase variables by GSPECT-MPI correlate well with tissue Doppler imaging by echocardiography. Main phase variables quantified by GSPECT-MPI are entropy, bandwidth, and phase standard deviation. Although those variables are automatically obtained from several software packages including Quantitative Gated SPECT and Emory Cardiac Toolbox, the methods for their measurement vary in each package. Several studies have shown that phase analysis has predictive value for response to cardiac resynchronization therapy and prognostic value for future adverse cardiac events beyond standard GSPECT-MPI variables. In this review, we summarize the basics of phase analysis on GSPECT-MPI and usefulness of phase analysis in clinical practice.

Direct Risk Assessment From Myocardial Perfusion Imaging Using Explainable Deep Learning.

BACKGROUND: Myocardial perfusion imaging (MPI) is frequently used to provide risk stratification, but methods to improve the accuracy of these predictions are needed. OBJECTIVES: The authors developed an explainable deep learning (DL) model (HARD MACE [major adverse cardiac events]-DL) for the prediction of death or nonfatal myocardial infarction (MI) and validated its performance in large internal and external testing groups. METHODS: Patients undergoing single-photon emission computed tomography MPI were included, with 20,401 patients in the training and internal testing group (5 sites) and 9,019 in the external testing group (2 different sites). HARD MACE-DL uses myocardial perfusion, motion, thickening, and phase polar maps combined with age, sex, and cardiac volumes. The primary outcome was all-cause mortality or nonfatal MI. Prognostic accuracy was evaluated using area under the receiver-operating characteristic curve (AUC). RESULTS: During internal testing, patients with normal perfusion and elevated HARD MACE-DL risk were at higher risk than patients with abnormal perfusion and low HARD MACE-DL risk (annualized event rate, 2.9% vs 1.2%; P < 0.001). Patients in the highest quartile of HARD MACE-DL score had an annual rate of death or MI (4.8%) 10-fold higher than patients in the lowest quartile (0.48% per year). In external testing, the AUC for HARD MACE-DL (0.73; 95% CI: 0.71-0.75) was higher than a logistic regression model (AUC: 0.70), stress total perfusion deficit (TPD) (AUC: 0.65), and ischemic TPD (AUC: 0.63; all P < 0.01). Calibration, a measure of how well predicted risk matches actual risk, was excellent in both groups (Brier score, 0.079 for internal and 0.070 for external). CONCLUSIONS: The DL model predicts death or MI directly from MPI, by estimating patient-level risk with good calibration and improved accuracy compared with traditional quantitative approaches. The model incorporates mechanisms to explain to the physician which image regions contribute to the adverse event prediction.

Deep Learning of Coronary Calcium Scores From PET/CT Attenuation Maps Accurately Predicts Adverse Cardiovascular Events.

BACKGROUND: Assessment of coronary artery calcium (CAC) by computed tomographic (CT) imaging provides an accurate measure of atherosclerotic burden. CAC is also visible in computed tomographic attenuation correction (CTAC) scans, always acquired with cardiac positron emission tomographic (PET) imaging. OBJECTIVES: The aim of this study was to develop a deep-learning (DL) model capable of fully automated CAC definition from PET CTAC scans. METHODS: The novel DL model, originally developed for video applications, was adapted to rapidly quantify CAC. The model was trained using 9,543 expert-annotated CT scans and was tested in 4,331 patients from an external cohort undergoing PET/CT imaging with major adverse cardiac events (MACEs) (follow-up 4.3 years), including same-day paired electrocardiographically gated CAC scans available in 2,737 patients. MACE risk stratification in 4 CAC score categories (0, 1-100, 101-400, and >400) was analyzed and CAC scores derived from electrocardiographically gated CT scans (standard scores) by expert observers were compared with automatic DL scores from CTAC scans. RESULTS: Automatic DL scoring required <6 seconds per scan. DL CTAC scores provided stepwise increase in the risk for MACE across the CAC score categories (HR up to 3.2; P < 0.001). Net reclassification improvement of standard CAC scores over DL CTAC scores was nonsignificant (-0.02; 95% CI: -0.11 to 0.07). The negative predictive values for MACE of zero CAC with standard (85%) and DL CTAC (83%) CAC scores were similar (P = 0.19). CONCLUSIONS: DL CTAC scores predict cardiovascular risk similarly to standard CAC scores quantified manually by experienced operators from dedicated electrocardiographically gated CAC scans and can be obtained almost instantly, with no changes to PET/CT scanning protocol.

Deep Learning Coronary Artery Calcium Scores from SPECT/CT Attenuation Maps Improve Prediction of Major Adverse Cardiac Events.

Low-dose ungated CT attenuation correction (CTAC) scans are commonly obtained with SPECT/CT myocardial perfusion imaging. Despite the characteristically low image quality of CTAC, deep learning (DL) can potentially quantify coronary artery calcium (CAC) from these scans in an automatic manner. We evaluated CAC quantification derived with a DL model, including correlation with expert annotations and associations with major adverse cardiovascular events (MACE). Methods: We trained a convolutional long short-term memory DL model to automatically quantify CAC on CTAC scans using 6,608 studies (2 centers) and evaluated the model in an external cohort of patients without known coronary artery disease (n = 2,271) obtained in a separate center. We assessed agreement between DL and expert annotated CAC scores. We also assessed associations between MACE (death, revascularization, myocardial infarction, or unstable angina) and CAC categories (0, 1-100, 101-400, or >400) for scores manually derived by experienced readers and scores obtained fully automatically by DL using multivariable Cox models (adjusted for age, sex, past medical history, perfusion, and ejection fraction) and net reclassification index. Results: In the external testing population, DL CAC was 0 in 908 patients (40.0%), 1-100 in 596 (26.2%), 100-400 in 354 (15.6%), and >400 in 413 (18.2%). Agreement in CAC category by DL CAC and expert annotation was excellent (linear weighted κ, 0.80), but DL CAC was obtained automatically in less than 2 s compared with about 2.5 min for expert CAC. DL CAC category was an independent risk factor for MACE with hazard ratios in comparison to a CAC of zero: CAC of 1-100 (2.20; 95% CI, 1.54-3.14; P < 0.001), CAC of 101-400 (4.58; 95% CI, 3.23-6.48; P < 0.001), and CAC of more than 400 (5.92; 95% CI, 4.27-8.22; P < 0.001). Overall, the net reclassification index was 0.494 for DL CAC, which was similar to expert annotated CAC (0.503). Conclusion: DL CAC from SPECT/CT attenuation maps agrees well with expert CAC annotations and provides a similar risk stratification but can be obtained automatically. DL CAC scores improved classification of a significant proportion of patients as compared with SPECT myocardial perfusion alone.

Deep Learning for Explainable Estimation of Mortality Risk From Myocardial Positron Emission Tomography Images.

BACKGROUND: We aim to develop an explainable deep learning (DL) network for the prediction of all-cause mortality directly from positron emission tomography myocardial perfusion imaging flow and perfusion polar map data and evaluate it using prospective testing. METHODS: A total of 4735 consecutive patients referred for stress and rest 82Rb positron emission tomography between 2010 and 2018 were followed up for all-cause mortality for 4.15 (2.24-6.3) years. DL network utilized polar maps of stress and rest perfusion, myocardial blood flow, myocardial flow reserve, and spill-over fraction combined with cardiac volumes, singular indices, and sex. Patients scanned from 2010 to 2016 were used for training and validation. The network was tested in a set of 1135 patients scanned from 2017 to 2018 to simulate prospective clinical implementation. RESULTS: In prospective testing, the area under the receiver operating characteristic curve for all-cause mortality prediction by DL (0.82 [95% CI, 0.77-0.86]) was higher than ischemia (0.60 [95% CI, 0.54-0.66]; P <0.001), myocardial flow reserve (0.70 [95% CI, 0.64-0.76], P <0.001) or a comprehensive logistic regression model (0.75 [95% CI, 0.69-0.80], P <0.05). The highest quartile of patients by DL had an annual all-cause mortality rate of 11.87% and had a 16.8 ([95% CI, 6.12%-46.3%]; P <0.001)-fold increase in the risk of death compared with the lowest quartile patients. DL showed a 21.6% overall reclassification improvement as compared with established measures of ischemia. CONCLUSIONS: The DL model trained directly on polar maps allows improved patient risk stratification in comparison with established methods for positron emission tomography flow or perfusion assessments.

Reproducibility of quantitative coronary calcium scoring from PET/CT attenuation maps: comparison to ECG-gated CT scans.

PURPOSE: We sought to evaluate inter-scan and inter-reader agreement of coronary calcium (CAC) scores obtained from dedicated, ECG-gated CAC scans (standard CAC scan) and ultra-low-dose, ungated computed tomography attenuation correction (CTAC) scans obtained routinely during cardiac PET/CT imaging. METHODS: From 2928 consecutive patients who underwent same-day 82Rb cardiac PET/CT and gated CAC scan in the same hybrid PET/CT scanning session, we have randomly selected 200 cases with no history of revascularization. Standard CAC scans and ungated CTAC scans were scored by two readers using quantitative clinical software. We assessed the agreement between readers and between two scan protocols in 5 CAC categories (0, 1-10, 11-100, 101-400, and > 400) using Cohen's Kappa and concordance. RESULTS: Median age of patients was 70 (inter-quartile range: 63-77), and 46% were male. The inter-scan concordance index and Cohen's Kappa for readers 1 and 2 were 0.69; 0.75 (0.69, 0.81) and 0.72; 0.8 (0.75, 0.85) respectively. The inter-reader concordance index and Cohen's Kappa (95% confidence interval [CI]) was higher for standard CAC scans: 0.9 and 0.92 (0.89, 0.96), respectively, vs. for CTAC scans: 0.83 and 0.85 (0.79, 0.9) for CTAC scans (p = 0.02 for difference in Kappa). Most discordant readings between two protocols occurred for scans with low extent of calcification (CAC score < 100). CONCLUSION: CAC can be quantitatively assessed on PET CTAC maps with good agreement with standard scans, however with limited sensitivity for small lesions. CAC scoring of CTAC can be performed routinely without modification of PET protocol and added radiation dose.

Handling missing values in machine learning to predict patient-specific risk of adverse cardiac events: Insights from REFINE SPECT registry.

BACKGROUND: Machine learning (ML) models can improve prediction of major adverse cardiovascular events (MACE), but in clinical practice some values may be missing. We evaluated the influence of missing values in ML models for patient-specific prediction of MACE risk. METHODS: We included 20,179 patients from the multicenter REFINE SPECT registry with MACE follow-up data. We evaluated seven methods for handling missing values: 1) removal of variables with missing values (ML-Remove), 2) imputation with median and unique category for continuous and categorical variables, respectively (ML-Traditional), 3) unique category for missing variables (ML-Unique), 4) cluster-based imputation (ML-Cluster), 5) regression-based imputation (ML-Regression), 6) missRanger imputation (ML-MR), and 7) multiple imputation (ML-MICE). We trained ML models with full data and simulated missing values in testing patients. Prediction performance was evaluated using area under the receiver-operating characteristic curve (AUC) and compared with a model without missing values (ML-All), expert visual diagnosis and total perfusion deficit (TPD). RESULTS: During mean follow-up of 4.7 ± 1.5 years, 3,541 patients experienced at least one MACE (3.7% annualized risk). ML-All (reference model-no missing values) had AUC 0.799 for MACE risk prediction. All seven models with missing values had lower AUC (ML-Remove: 0.778, ML-MICE: 0.774, ML-Cluster: 0.771, ML-Traditional: 0.771, ML-Regression: 0.770, ML-MR: 0.766, and ML-Unique: 0.766; p < 0.01 for ML-Remove vs remaining methods). Stress TPD (AUC 0.698) and visual diagnosis (0.681) had the lowest AUCs. CONCLUSION: Missing values reduce the accuracy of ML models when predicting MACE risk. Removing variables with missing values and retraining the model may yield superior patient-level prediction performance.

Improved myocardial blood flow estimation with residual activity correction and motion correction in 18F-flurpiridaz PET myocardial perfusion imaging.

PURPOSE: We sought to evaluate the diagnostic performance for coronary artery disease (CAD) of myocardial blood flow (MBF) quantification with 18F-flurpiridaz PET using motion correction (MC) and residual activity correction (RAC). METHODS: In total, 231 patients undergoing same-day pharmacologic rest and stress 18F-flurpiridaz PET from Phase III Flurpiridaz trial (NCT01347710) were studied. Frame-by-frame MC was performed and RAC was accomplished by subtracting the rest residual counts from the dynamic stress polar maps. MBF and myocardial flow reserve (MFR) were derived with a two-compartment early kinetic model for the entire left ventricle (global), each coronary territory, and 17-segment. Global and minimal values of three territorial (minimal vessel) and segmental estimation (minimal segment) of stress MBF and MFR were evaluated in the prediction of CAD. MBF and MFR were evaluated with and without MC and RAC (1: no MC/no RAC, 2: no MC/RAC, 3: MC/RAC). RESULTS: The area-under the receiver operating characteristics curve (AUC [95% confidence interval]) of stress MBF with MC/RAC was higher for minimal segment (0.89 [0.85-0.94]) than for minimal vessel (0.86 [0.81-0.92], p = 0.03) or global estimation (0.81 [0.75-0.87], p < 0.0001). The AUC of MFR with MC/RAC was higher for minimal segment (0.87 [0.81-0.93]) than for minimal vessel (0.83 [0.76-0.90], p = 0.014) or global estimation (0.77 [0.69-0.84], p < 0.0001). The AUCs of minimal segment stress MBF and MFR with MC/RAC were higher compared to those with no MC/RAC (p < 0.001 for both) or no MC/no RAC (p < 0.0001 for both). CONCLUSIONS: Minimal segment MBF or MFR estimation with MC and RAC improves the diagnostic performance for obstructive CAD compared to global assessment.

Determining a minimum set of variables for machine learning cardiovascular event prediction: results from REFINE SPECT registry.

AIMS: Optimal risk stratification with machine learning (ML) from myocardial perfusion imaging (MPI) includes both clinical and imaging data. While most imaging variables can be derived automatically, clinical variables require manual collection, which is time-consuming and prone to error. We determined the fewest manually input and imaging variables required to maintain the prognostic accuracy for major adverse cardiac events (MACE) in patients undergoing a single-photon emission computed tomography (SPECT) MPI. METHODS AND RESULTS: This study included 20 414 patients from the multicentre REFINE SPECT registry and 2984 from the University of Calgary for training and external testing of the ML models, respectively. ML models were trained using all variables (ML-All) and all image-derived variables (including age and sex, ML-Image). Next, ML models were sequentially trained by incrementally adding manually input and imaging variables to baseline ML models based on their importance ranking. The fewest variables were determined as the ML models (ML-Reduced, ML-Minimum, and ML-Image-Reduced) that achieved comparable prognostic performance to ML-All and ML-Image. Prognostic accuracy of the ML models was compared with visual diagnosis, stress total perfusion deficit (TPD), and traditional multivariable models using area under the receiver-operating characteristic curve (AUC). ML-Minimum (AUC 0.798) obtained comparable prognostic accuracy to ML-All (AUC 0.799, P = 0.19) by including 12 of 40 manually input variables and 11 of 58 imaging variables. ML-Reduced achieved comparable accuracy (AUC 0.796) with a reduced set of manually input variables and all imaging variables. In external validation, the ML models also obtained comparable or higher prognostic accuracy than traditional multivariable models. CONCLUSION: Reduced ML models, including a minimum set of manually collected or imaging variables, achieved slightly lower accuracy compared to a full ML model but outperformed standard interpretation methods and risk models. ML models with fewer collected variables may be more practical for clinical implementation.

Prognostic Value of Phase Analysis for Predicting Adverse Cardiac Events Beyond Conventional Single-Photon Emission Computed Tomography Variables: Results From the REFINE SPECT Registry.

BACKGROUND: Phase analysis of single-photon emission computed tomography myocardial perfusion imaging provides dyssynchrony information which correlates well with assessments by echocardiography, but the independent prognostic significance is not well defined. This study assessed the independent prognostic value of single-photon emission computed tomography-myocardial perfusion imaging phase analysis in the largest multinational registry to date across all modalities. METHODS: From the REFINE SPECT (Registry of Fast Myocardial Perfusion Imaging With Next Generation SPECT), a total of 19 210 patients were included (mean age 63.8±12.0 years and 56% males). Poststress total perfusion deficit, left ventricular ejection fraction, and phase variables (phase entropy, bandwidth, and SD) were obtained automatically. Cox proportional hazards analyses were performed to assess associations with major adverse cardiac events (MACE). RESULTS: During a follow-up of 4.5±1.7 years, 2673 (13.9%) patients experienced MACE. Annualized MACE rates increased with phase variables and were ≈4-fold higher between the second and highest decile group for entropy (1.7% versus 6.7%). Optimal phase variable cutoff values stratified MACE risk in patients with normal and abnormal total perfusion deficit and left ventricular ejection fraction. Only entropy was independently associated with MACE. The addition of phase entropy significantly improved the discriminatory power for MACE prediction when added to the model with total perfusion deficit and left ventricular ejection fraction (P<0.0001). CONCLUSIONS: In a largest to date imaging study, widely representative, international cohort, phase variables were independently associated with MACE and improved risk stratification for MACE beyond the prediction by perfusion and left ventricular ejection fraction assessment alone. Phase analysis can be obtained fully automatically, without additional radiation exposure or cost to improve MACE risk prediction and, therefore, should be routinely reported for single-photon emission computed tomography-myocardial perfusion imaging studies.

Influence of SPECT attenuation correction on the quantification of hibernating myocardium as derived from combined myocardial perfusion SPECT and ¹8F-FDG PET.

BACKGROUND: To evaluate the influence of SPECT attenuation correction on the quantification of hibernating myocardium derived from perfusion SPECT and (18)F-FDG PET. METHODS AND RESULTS: 20 patients underwent rest (99m)Tc-tetrofosmin perfusion SPECT/CT and (18)F-FDG PET/CT. Perfusion images were reconstructed without attenuation correction (NC), with attenuation correction based on the CT from the SPECT/CT (AC_SPECT), and with attenuation correction based on the CT from the PET/CT (AC_PET). Another 56 patients had rest (99m)Tc-tetrofosmin perfusion SPECT and (18)F-FDG PET/CT. Perfusion images were reconstructed as NC and AC_PET. The amounts of hibernating myocardium and scar were quantified with QPS and corresponding AC and NC normative databases. In both cohorts, perfusion in the inferior wall was higher in the AC scans than without AC. Global and regional values for total perfusion deficit (TPD), hibernation and scar areas did not differ between NC, AC_SPECT, and AC_PET scans. In a retrospective evaluation with 7% cut-off of hibernating myocardium as a condition for revascularization, the therapeutic approach would have been altered in 5 of 56 patients, if the AC_PET approach had been used. CONCLUSIONS: AC of SPECT perfusion scans with an attenuation map derived from PET/CT scans is feasible. If AC is unavailable, perfusion scans should be compared to NC normative databases for assessing TPD, hibernation, and mismatch. It should be taken into account that in approximately 10% of the patients, a therapeutic recommendation based on published thresholds for hibernating myocardium would be altered if NC scans were used as compared to AC scans.

The amount of viable and dyssynchronous myocardium is associated with response to cardiac resynchronization therapy: initial clinical results using multiparametric ECG-gated [18F]FDG PET.

PURPOSE: There is still a significant amount of patients who do not sufficiently respond to cardiac resynchronization therapy (CRT). Previous studies demonstrated that the amount of dyssynchronous myocardium was predictive of response to CRT. Otherwise, non-response is frequently associated with high amounts of scar tissue. The combination of these parameters might yield a more accurate prediction of response. We hypothesized that the probability of a CRT response increases with the presence of high amounts of "viable and dyssynchronous" myocardium. METHODS: A total of 19 patients (17 male, 61 ± 10 years) underwent ECG-gated [(18)F]fluorodeoxyglucose (FDG) myocardial positron emission tomography (PET) before CRT device implantation and were followed for 6 months. Response to CRT was defined as clinical improvement of at least one New York Heart Association (NYHA) class in combination with left ventricular (LV) ejection fraction (EF) improvement of >5%. Twelve responders (71%) and seven non-responders (29%) were identified. For each patient bullseye maps of FDG uptake and phase analysis were calculated (QPS/QGS 2012, Cedars-Sinai, Los Angeles, CA, USA) and fused. Amounts of myocardium representing "viable and synchronous", "scar and synchronous", viable and dyssynchronous or "scar and dyssynchronous" myocardium were quantified by planimetric measurements of the fused bullseye maps. RESULTS: Responders by definition showed significant decrease in NYHA class and significant increase of LVEF. Furthermore, a significantly higher amount of viable and dyssynchronous myocardium was found as compared to non-responders (21 ± 13% vs 6 ± 5%; p < 0.05). CONCLUSION: Combined assessment of myocardial viability and LV dyssynchrony is feasible using multiparametric [(18)F]FDG PET and could improve conventional response prediction criteria for CRT.