Mitigating bias in deep learning for diagnosis of coronary artery disease from myocardial perfusion SPECT images.

PURPOSE: Artificial intelligence (AI) has high diagnostic accuracy for coronary artery disease (CAD) from myocardial perfusion imaging (MPI). However, when trained using high-risk populations (such as patients with correlating invasive testing), the disease probability can be overestimated due to selection bias. We evaluated different strategies for training AI models to improve the calibration (accurate estimate of disease probability), using external testing. METHODS: Deep learning was trained using 828 patients from 3 sites, with MPI and invasive angiography within 6 months. Perfusion was assessed using upright (U-TPD) and supine total perfusion deficit (S-TPD). AI training without data augmentation (model 1) was compared to training with augmentation (increased sampling) of patients without obstructive CAD (model 2), and patients without CAD and TPD < 2% (model 3). All models were tested in an external population of patients with invasive angiography within 6 months (n = 332) or low likelihood of CAD (n = 179). RESULTS: Model 3 achieved the best calibration (Brier score 0.104 vs 0.121, p < 0.01). Improvement in calibration was particularly evident in women (Brier score 0.084 vs 0.124, p < 0.01). In external testing (n = 511), the area under the receiver operating characteristic curve (AUC) was higher for model 3 (0.930), compared to U-TPD (AUC 0.897) and S-TPD (AUC 0.900, p < 0.01 for both). CONCLUSION: Training AI models with augmentation of low-risk patients can improve calibration of AI models developed to identify patients with CAD, allowing more accurate assignment of disease probability. This is particularly important in lower-risk populations and in women, where overestimation of disease probability could significantly influence down-stream patient management.

Unsupervised learning to characterize patients with known coronary artery disease undergoing myocardial perfusion imaging.

PURPOSE: Patients with known coronary artery disease (CAD) comprise a heterogenous population with varied clinical and imaging characteristics. Unsupervised machine learning can identify new risk phenotypes in an unbiased fashion. We use cluster analysis to risk-stratify patients with known CAD undergoing single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). METHODS: From 37,298 patients in the REFINE SPECT registry, we identified 9221 patients with known coronary artery disease. Unsupervised machine learning was performed using clinical (23), acquisition (17), and image analysis (24) parameters from 4774 patients (internal cohort) and validated with 4447 patients (external cohort). Risk stratification for all-cause mortality was compared to stress total perfusion deficit (< 5%, 5-10%, ≥10%). RESULTS: Three clusters were identified, with patients in Cluster 3 having a higher body mass index, more diabetes mellitus and hypertension, and less likely to be male, have dyslipidemia, or undergo exercise stress imaging (p < 0.001 for all). In the external cohort, during median follow-up of 2.6 [0.14, 3.3] years, all-cause mortality occurred in 312 patients (7%). Cluster analysis provided better risk stratification for all-cause mortality (Cluster 3: hazard ratio (HR) 5.9, 95% confidence interval (CI) 4.0, 8.6, p < 0.001; Cluster 2: HR 3.3, 95% CI 2.5, 4.5, p < 0.001; Cluster 1, reference) compared to stress total perfusion deficit (≥10%: HR 1.9, 95% CI 1.5, 2.5 p < 0.001; < 5%: reference). CONCLUSIONS: Our unsupervised cluster analysis in patients with known CAD undergoing SPECT MPI identified three distinct phenotypic clusters and predicted all-cause mortality better than ischemia alone.

Prognostic value of early left ventricular ejection fraction reserve during regadenoson stress solid-state SPECT-MPI.

BACKGROUND: We hypothesized early post-stress left ventricular ejection fraction reserve (EFR) on solid-state-SPECT is associated with major cardiac adverse events (MACE). METHODS: 151 patients (70 ± 12 years, male 50%) undergoing same-day rest/regadenoson stress 99mTc-sestamibi solid-state SPECT were followed for MACE. Rest imaging was performed in the upright and supine positions. Early stress imaging was started 2 minutes after the regadenoson injection in the supine position and followed by late stress acquisition in the upright position. Total perfusion deficit (TPD) and functional parameters were quantified automatically. EFR, ∆end-diastolic volume (EDV), and end-systolic volume (ESV) were calculated as the difference between stress and rest values in the same position. EFR < 0%, ∆EDV ≥ 5 ml, or ∆ESV ≥ 5 ml was defined as abnormal. RESULTS: During the follow-up (mean 3.2 years), 28 MACE occurred (19%). In Kaplan-Meier analysis, there was a significantly decreased event-free survival in patients with early EFR < 0% (P = 0.004). Similarly, there was a decreased event-free survival in patients with ∆ESV ≥ 5 ml at early stress (P = 0.003). However, EFR, ∆EDV, and ∆ESV at late stress were not associated with MACE-free survival. Cox proportional hazards model adjusting for clinical information and stress TPD demonstrated that EFR, ∆EDV, and ∆ESV at early stress were significantly associated with MACE (P < 0.05 for all). CONCLUSIONS: Reduced early post-stress EFR on vasodilator stress solid-state SPECT is associated with MACE.

Machine learning to predict abnormal myocardial perfusion from pre-test features.

BACKGROUND: Accurately predicting which patients will have abnormal perfusion on MPI based on pre-test clinical information may help physicians make test selection decisions. We developed and validated a machine learning (ML) model for predicting abnormal perfusion using pre-test features. METHODS: We included consecutive patients who underwent SPECT MPI, with 20,418 patients from a multi-center (5 sites) international registry in the training population and 9019 patients (from 2 separate sites) in the external testing population. The ML (extreme gradient boosting) model utilized 30 pre-test features to predict the presence of abnormal myocardial perfusion by expert visual interpretation. RESULTS: In external testing, the ML model had higher prediction performance for abnormal perfusion (area under receiver-operating characteristic curve [AUC] 0.762, 95% CI 0.750-0.774) compared to the clinical CAD consortium (AUC 0.689) basic CAD consortium (AUC 0.657), and updated Diamond-Forrester models (AUC 0.658, p < 0.001 for all). Calibration (validation of the continuous risk prediction) was superior for the ML model (Brier score 0.149) compared to the other models (Brier score 0.165 to 0.198, all p < 0.001). CONCLUSION: ML can predict abnormal myocardial perfusion using readily available pre-test information. This model could be used to help guide physician decisions regarding non-invasive test selection.

Prevalence and predictors of automatically quantified myocardial ischemia within a multicenter international registry.

BACKGROUND: The utility of cardiac stress testing depends on the prevalence of myocardial ischemia within candidate populations. However, a comprehensive assessment of the factors influencing frequency of myocardial ischemia within contemporary populations referred for stress testing has not been performed. METHODS: We assessed 19,690 patients undergoing nuclear stress testing from a multicenter registry. The chi-square test was used to assess the relative importance of features for predicting myocardial ischemia. RESULTS: In the overall cohort, LVEF, male gender, and rest total perfusion deficit (TPD) were the top three predictors of ischemia, followed by CAD status, age, typical angina, and CAD risk factors. Myocardial ischemia was observed in 13.6 % of patients with LVEF > 55 %, in 26.2 % of patients with LVEF 45 %-54 %, and in 48.3% among patients with LVEF < 45 % (P < 0.001). A similar pattern was noted for rest TPD (P < 0.001). Men had a threefold higher frequency of ischemia versus women (25.8 % vs. 8.4%, P < 0.001). Although the relative ranking of ischemia predictors varied among centers, LVEF and/or rest TPD were among the two most potent predictors of myocardial ischemia within each center. CONCLUSION: The prevalence of myocardial ischemia varied markedly according to clinical and imaging characteristics. LVEF and rest TPD are robust predictors of myocardial ischemia.

Automated quantitative analysis of CZT SPECT stratifies cardiovascular risk in the obese population: Analysis of the REFINE SPECT registry.

BACKGROUND: Obese patients constitute a substantial proportion of patients referred for SPECT myocardial perfusion imaging (MPI), presenting a challenge of increased soft tissue attenuation. We investigated whether automated quantitative perfusion analysis can stratify risk among different obesity categories and whether two-view acquisition adds to prognostic assessment. METHODS: Participants were categorized according to body mass index (BMI). SPECT MPI was assessed visually and quantified automatically; combined total perfusion deficit (TPD) was evaluated. Kaplan-Meier and Cox proportional hazard analyses were used to assess major adverse cardiac event (MACE) risk. Prognostic accuracy for MACE was also compared. RESULTS: Patients were classified according to BMI: BMI < 30, 30 ≤ BMI < 35, BMI ≥ 35. In adjusted analysis, each category of increasing stress TPD was associated with increased MACE risk, except for 1% ≤ TPD < 5% and 5% ≤ TPD < 10% in patients with BMI ≥ 35. Compared to visual analysis, single-position stress TPD had higher prognostic accuracy in patients with BMI < 30 (AUC .652 vs .631, P < .001) and 30 ≤ BMI < 35 (AUC .660 vs .636, P = .027). Combined TPD had better discrimination than visual analysis in patients with BMI ≥ 35 (AUC .662 vs .615, P = .003). CONCLUSIONS: Automated quantitative methods for SPECT MPI interpretation provide robust risk stratification in the obese population. Combined stress TPD provides additional prognostic accuracy in patients with more significant obesity.

Diagnostic safety of a machine learning-based automatic patient selection algorithm for stress-only myocardial perfusion SPECT.

BACKGROUND: Stress-only myocardial perfusion imaging (MPI) markedly reduces radiation dose, scanning time, and cost. We developed an automated clinical algorithm to safely cancel unnecessary rest imaging with high sensitivity for obstructive coronary artery disease (CAD). METHODS AND RESULTS: Patients without known CAD undergoing both MPI and invasive coronary angiography from REFINE SPECT were studied. A machine learning score (MLS) for prediction of obstructive CAD was generated using stress-only MPI and pre-test clinical variables. An MLS threshold with a pre-defined sensitivity of 95% was applied to the automated patient selection algorithm. Obstructive CAD was present in 1309/2079 (63%) patients. MLS had higher area under the receiver operator characteristic curve (AUC) for prediction of CAD than reader diagnosis and TPD (0.84 vs 0.70 vs 0.78, P < .01). An MLS threshold of 0.29 had superior sensitivity than reader diagnosis and TPD for obstructive CAD (95% vs 87% vs 87%, P < .01) and high-risk CAD, defined as stenosis of the left main, proximal left anterior descending, or triple-vessel CAD (sensitivity 96% vs 89% vs 90%, P < .01). CONCLUSIONS: The MLS is highly sensitive for prediction of both obstructive and high-risk CAD from stress-only MPI and can be applied to a stress-first protocol for automatic cancellation of unnecessary rest imaging.

Comparison of diabetes to other prognostic predictors among patients referred for cardiac stress testing: A contemporary analysis from the REFINE SPECT Registry.

BACKGROUND: Diabetes mellitus (DM) is increasingly prevalent among contemporary populations referred for cardiac stress testing, but its potency as a predictor for major adverse cardiovascular events (MACE) vs other clinical variables is not well delineated. METHODS AND RESULTS: From 19,658 patients who underwent SPECT-MPI, we identified 3122 patients with DM without known coronary artery disease (CAD) (DM+/CAD-) and 3564 without DM with known CAD (DM-/CAD+). Propensity score matching was used to control for the differences in characteristics between DM+/CAD- and DM-/CAD+ groups. There was comparable MACE in the matched DM+/CAD- and DM-/CAD+ groups (HR 1.15, 95% CI 0.97-1.37). By Chi-square analysis, type of stress (exercise or pharmacologic), total perfusion deficit (TPD), and left ventricular function were the most potent predictors of MACE, followed by CAD and DM status. The combined consideration of mode of stress, TPD, and DM provided synergistic stratification, an 8.87-fold (HR 8.87, 95% CI 7.27-10.82) increase in MACE among pharmacologically stressed patients with DM and TPD > 10% (vs non-ischemic, exercised stressed patients without DM). CONCLUSIONS: Propensity-matched patients with DM and no known CAD have similar MACE risk compared to patients with known CAD and no DM. DM is synergistic with mode of stress testing and TPD in predicting the risk of cardiac stress test patients.

Rationale and design of the REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT (REFINE SPECT).

BACKGROUND: We aim to establish a multicenter registry collecting clinical, imaging, and follow-up data for patients who undergo myocardial perfusion imaging (MPI) with the latest generation SPECT scanners. METHODS: REFINE SPECT (REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT) uses a collaborative design with multicenter contribution of clinical data and images into a comprehensive clinical-imaging database. All images are processed by quantitative software. Over 290 individual imaging variables are automatically extracted from each image dataset and merged with clinical variables. In the prognostic cohort, patient follow-up is performed for major adverse cardiac events. In the diagnostic cohort (patients with correlating invasive angiography), angiography and revascularization results within 6 months are obtained. RESULTS: To date, collected prognostic data include scans from 20,418 patients in 5 centers (57% male, 64.0 ± 12.1 years) who underwent exercise (48%) or pharmacologic stress (52%). Diagnostic data include 2079 patients in 9 centers (67% male, 64.7 ± 11.2 years) who underwent exercise (39%) or pharmacologic stress (61%). CONCLUSION: The REFINE SPECT registry will provide a resource for collaborative projects related to the latest generation SPECT-MPI. It will aid in the development of new artificial intelligence tools for automated diagnosis and prediction of prognostic outcomes.

Upper reference limits of transient ischemic dilation ratio for different protocols on new-generation cadmium zinc telluride cameras: A report from REFINE SPECT registry.

BACKGROUND: Upper reference limits for transient ischemic dilation (TID) have not been rigorously established for cadmium-zinc-telluride (CZT) camera systems. We aimed to derive TID limits for common myocardial perfusion imaging protocols utilizing a large, multicenter registry (REFINE SPECT). METHODS: One thousand six hundred and seventy-two patients with low likelihood of coronary artery disease with normal perfusion findings were identified. Images were processed with Quantitative Perfusion SPECT software (Cedars-Sinai Medical Center, Los Angeles, CA). Non-attenuation-corrected, camera-, radiotracer-, and stress protocol-specific TID limits in supine position were derived from 97.5th percentile and mean + 2 standard deviations (SD). Reference limits were compared for different solid-state cameras (D-SPECT vs. Discovery), radiotracers (technetium-99m-sestamibi vs. tetrofosmin), different types of stress (exercise vs. four different vasodilator-based protocols), and different vasodilator-based protocols. RESULTS: TID measurements did not follow Gaussian distribution in six out of eight subgroups. TID limits ranged from 1.18 to 1.52 (97.5th percentile) and 1.18 to 1.39 (mean + 2SD). No difference was noted between D-SPECT and Discovery cameras (P = 0.71) while differences between exercise and vasodilator-based protocols (adenosine, regadenoson, or regadenoson-walk) were noted (all P < 0.05). CONCLUSIONS: We used a multicenter registry to establish camera-, radiotracer-, and protocol-specific upper reference limits of TID for supine position on CZT camera systems. Reference limits did not differ between D-SPECT and Discovery camera.

Quantitation of left ventricular ejection fraction reserve from early gated regadenoson stress Tc-99m high-efficiency SPECT.

BACKGROUND: Ejection fraction (EF) reserve has been found to be a useful adjunct for identifying high risk coronary artery disease in cardiac positron emission tomography (PET). We aimed to evaluate EF reserve obtained from technetium-99m sestamibi (Tc-99m) high-efficiency (HE) SPECT. METHODS: Fifty patients (mean age 69 years) undergoing regadenoson same-day rest (8-11 mCi)/stress (32-42 mCi) Tc-99m gated HE SPECT were enrolled. Stress imaging was started 1 minute after sequential intravenous regadenoson .4 mg and Tc-99m injections, and was composed of five 2 minutes supine gated acquisitions followed by two 4 minutes supine and upright images. Ischemic total perfusion deficit (ITPD) ≥5 % was considered as significant ischemia. RESULTS: Significantly lower mean EF reserve was obtained in the 5th and 9th minute after regadenoson bolus in patients with significant ischemia vs patients without (5th minute: -4.2 ± 4.6% vs 1.3 ± 6.6%, P = .006; 9th minute: -2.7 ± 4.8% vs 2.0 ± 6.6%, P = .03). CONCLUSIONS: Negative EF reserve obtained between 5th and 9th minutes of regadenoson stress demonstrated best concordance with significant ischemia and may be a promising tool for detection of transient ischemic functional changes with Tc-99m HE-SPECT.

"Same-Patient Processing" for multiple cardiac SPECT studies. 1. Improving LV segmentation accuracy.

OBJECTIVES: This paper describes a novel approach (same-patient processing, or SPP) aimed at improving left ventricular segmentation accuracy in patients with multiple SPECT studies, and evaluates its performance compared to conventional processing in a large population of 962 patients undergoing rest and stress electrocardiography-gated SPECT MPI, for a total of 5,772 image datasets (6 per patient). METHODS: Each dataset was independently processed using a standard algorithm, and a shape quality control score (SQC) was produced for every segmentation. Datasets with a SQC score higher than a specific threshold, suggesting algorithmic failure, were automatically reprocessed with the SPP-modified algorithm, which incorporates knowledge of the segmentation mask location in the other datasets belonging to the same patient. Experienced operators blinded as to whether datasets had been processed based on the standard or SPP approach assessed segmentation success/failure for each dataset. RESULTS: The SPP approach reduced segmentation failures from 219/5772 (3.8%) to 42/5772 (0.7%) overall, with particular improvements in attenuation corrected (AC) datasets with high extra-cardiac activity (from 100/962 (10.4%) to 12/962 (1.4%) for rest AC, and from 41/962 (4.3%) to 9/962 (0.9%) for stress AC). The number of patients who had at least one of their 6 datasets affected by segmentation failure decreased from 141/962 (14.7%) to 14/962 (1.7%) using the SPP approach. CONCLUSION: Whenever multiple image datasets for the same patient exist and need to be processed, it is possible to deal with the images as a group rather than individually. The same-patient processing approach can be implemented automatically, and may substantially reduce the need for manual reprocessing due to cardiac segmentation failure.

Predictors of high-risk coronary artery disease in subjects with normal SPECT myocardial perfusion imaging.

BACKGROUND: While uncommon, normal stress SPECT myocardial perfusion imaging (MPI) can be seen in patients with high-risk coronary artery disease (CAD) by invasive coronary angiography (ICA).The predictors of high-risk CAD in patients with normal SPECT-MPI have not been described. METHODS: We studied 580 patients (age 64 ± 12 years, 49% men) without known CAD who underwent stress-gated SPECT-MPI [exercise (41%) or vasodilator (59%)] <2 months before ICA and had summed stress score (SSS) <4. High-risk CAD was defined as 3 vessels with ≥70% stenosis, 2 vessels with ≥70% stenosis including proximal left anterior descending, or left main with ≥50% stenosis. Obstructive non-high-risk CAD was defined by the presence of a ≥70% stenosis but without having other high-risk criteria. Tenfold cross-validated receiver operating characteristic (ROC) estimates were obtained to assess the predictors of high-risk CAD. RESULTS: Forty-two subjects (7.2%) had high-risk CAD and 168 (29.0%) had obstructive non-high-risk CAD. Variables associated with high-risk CAD were pretest probability of CAD ≥66% (Odds ratio [OR] 3.63, 95% CI 1.6-8.3, P = .002), SSS > 0 (OR 7.46, 95% CI 2.6-21.1, P < 0.001), and abnormal TID (OR 2.16, 95% CI 1.0-4.5, P = 0.044). When substituted for TID, EF change was also predictive of high-risk CAD (OR 0.93, 95% CI 0.9-1.0, P = 0.023). The prevalence of high-risk CAD increased as the number of these predictors increased. In a sub-analysis of patients in whom quantitative total perfusion deficit (TPD) was available, TPD > 0 was also a predictor of high-risk CAD (OR 6.01, 95% CI 1.5-22.2, P = 0.011). CONCLUSION: Several clinical, stress, and SPECT-MPI findings are associated high-risk CAD among patients with normal SPECT-MPI. Consideration of these factors may improve the overall assessment of the likelihood of high-risk CAD in patients undergoing stress SPECT-MPI.

Prediction of revascularization after myocardial perfusion SPECT by machine learning in a large population.

OBJECTIVE: We aimed to investigate if early revascularization in patients with suspected coronary artery disease can be effectively predicted by integrating clinical data and quantitative image features derived from perfusion SPECT (MPS) by machine learning (ML) approach. METHODS: 713 rest (201)Thallium/stress (99m)Technetium MPS studies with correlating invasive angiography with 372 revascularization events (275 PCI/97 CABG) within 90 days after MPS (91% within 30 days) were considered. Transient ischemic dilation, stress combined supine/prone total perfusion deficit (TPD), supine rest and stress TPD, exercise ejection fraction, and end-systolic volume, along with clinical parameters including patient gender, history of hypertension and diabetes mellitus, ST-depression on baseline ECG, ECG and clinical response during stress, and post-ECG probability by boosted ensemble ML algorithm (LogitBoost) to predict revascularization events. These features were selected using an automated feature selection algorithm from all available clinical and quantitative data (33 parameters). Tenfold cross-validation was utilized to train and test the prediction model. The prediction of revascularization by ML algorithm was compared to standalone measures of perfusion and visual analysis by two experienced readers utilizing all imaging, quantitative, and clinical data. RESULTS: The sensitivity of machine learning (ML) (73.6% ± 4.3%) for prediction of revascularization was similar to one reader (73.9% ± 4.6%) and standalone measures of perfusion (75.5% ± 4.5%). The specificity of ML (74.7% ± 4.2%) was also better than both expert readers (67.2% ± 4.9% and 66.0% ± 5.0%, P < .05), but was similar to ischemic TPD (68.3% ± 4.9%, P < .05). The receiver operator characteristics areas under curve for ML (0.81 ± 0.02) was similar to reader 1 (0.81 ± 0.02) but superior to reader 2 (0.72 ± 0.02, P < .01) and standalone measure of perfusion (0.77 ± 0.02, P < .01). CONCLUSION: ML approach is comparable or better than experienced readers in prediction of the early revascularization after MPS, and is significantly better than standalone measures of perfusion derived from MPS.

Quantitative high-efficiency cadmium-zinc-telluride SPECT with dedicated parallel-hole collimation system in obese patients: results of a multi-center study.

BACKGROUND: Obesity is a common source of artifact on conventional SPECT myocardial perfusion imaging (MPI). We evaluated image quality and diagnostic performance of high-efficiency (HE) cadmium-zinc-telluride parallel-hole SPECT MPI for coronary artery disease (CAD) in obese patients. METHODS AND RESULTS: 118 consecutive obese patients at three centers (BMI 43.6 ± 8.9 kg·m(-2), range 35-79.7 kg·m(-2)) had upright/supine HE-SPECT and invasive coronary angiography > 6 months (n = 67) or low likelihood of CAD (n = 51). Stress quantitative total perfusion deficit (TPD) for upright (U-TPD), supine (S-TPD), and combined acquisitions (C-TPD) was assessed. Image quality (IQ; 5 = excellent; < 3 nondiagnostic) was compared among BMI 35-39.9 (n = 58), 40-44.9 (n = 24) and ≥45 (n = 36) groups. ROC curve area for CAD detection (≥50% stenosis) for U-TPD, S-TPD, and C-TPD were 0.80, 0.80, and 0.87, respectively. Sensitivity/specificity was 82%/57% for U-TPD, 74%/71% for S-TPD, and 80%/82% for C-TPD. C-TPD had highest specificity (P = .02). C-TPD normalcy rate was higher than U-TPD (88% vs 75%, P = .02). Mean IQ was similar among BMI 35-39.9, 40-44.9 and ≥45 groups [4.6 vs 4.4 vs 4.5, respectively (P = .6)]. No patient had a nondiagnostic stress scan. CONCLUSIONS: In obese patients, HE-SPECT MPI with dedicated parallel-hole collimation demonstrated high image quality, normalcy rate, and diagnostic accuracy for CAD by quantitative analysis of combined upright/supine acquisitions.

Two-position supine/prone myocardial perfusion SPECT (MPS) imaging improves visual inter-observer correlation and agreement.

OBJECTIVES: We aimed to compare the inter-observer agreement between two experienced readers using supine vs combined supine/prone myocardial perfusion SPECT (MPS) in a large population. METHODS: 1,181 consecutive patients without known coronary artery disease (CAD) undergoing rest (201)Tl/stress (99m)Tc-sestamibi MPS studies were evaluated. Visual reads were performed in two consecutive steps, with readers scoring the stress supine perfusion images during step 1 and rescoring the images using both supine/prone data during step 2. Visual summed stress scores (SSS) of two readers including regional scores in different vascular territories were compared. RESULTS: The specificity for both readers improved using combined supine/prone imaging (reader 1: 92% vs 86% [P = .0002], reader 2: 88% vs 72% [P < .0001]). The inter-observer correlation for SSS (0.90 vs 0.84, P < .0001) and inter-observer agreement for combined supine/prone reading (bias = 1.0, 95% confidence interval (CI) 0.9-1.2 vs bias = 3.1, 95% CI 2.8-3.4, P < .0001) were significantly better as compared to supine-only reading. The overall correlation between SSS scores for two readers improved with supine/prone imaging for both genders, as well as in the left anterior descending and right coronary territories. CONCLUSION: The inter-observer correlation and agreement significantly improve using two-position supine/prone vs supine-only imaging.

Clinical phenotypes among patients with normal cardiac perfusion using unsupervised learning: a retrospective observational study.

BACKGROUND: Myocardial perfusion imaging (MPI) is one of the most common cardiac scans and is used for diagnosis of coronary artery disease and assessment of cardiovascular risk. However, the large majority of MPI patients have normal results. We evaluated whether unsupervised machine learning could identify unique phenotypes among patients with normal scans and whether those phenotypes were associated with risk of death or myocardial infarction. METHODS: Patients from a large international multicenter MPI registry (10 sites) with normal perfusion by expert visual interpretation were included in this cohort analysis. The training population included 9849 patients, and external testing population 12,528 patients. Unsupervised cluster analysis was performed, with separate training and external testing cohorts, to identify clusters, with four distinct phenotypes. We evaluated the clinical and imaging features of clusters and their associations with death or myocardial infarction. FINDINGS: Patients in Clusters 1 and 2 almost exclusively underwent exercise stress, while patients in Clusters 3 and 4 mostly required pharmacologic stress. In external testing, the risk for Cluster 4 patients (20.2% of population, unadjusted hazard ratio [HR] 6.17, 95% confidence interval [CI] 4.64-8.20) was higher than the risk associated with pharmacologic stress (HR 3.03, 95% CI 2.53-3.63), or previous myocardial infarction (HR 1.82, 95% CI 1.40-2.36). INTERPRETATION: Unsupervised learning identified four distinct phenotypes of patients with normal perfusion scans, with a significant proportion of patients at very high risk of myocardial infarction or death. Our results suggest a potential role for patient phenotyping to improve risk stratification of patients with normal imaging results. FUNDING: This work was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R35HL161195 to PS]. The REFINE SPECT database was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R01HL089765 to PS]. MCW was supported by the British Heart Foundation [FS/ICRF/20/26002].

Improved accuracy of myocardial perfusion SPECT for detection of coronary artery disease by machine learning in a large population.

OBJECTIVE: We aimed to improve the diagnostic accuracy of myocardial perfusion SPECT (MPS) by integrating clinical data and quantitative image features with machine learning (ML) algorithms. METHODS: 1,181 rest (201)Tl/stress (99m)Tc-sestamibi dual-isotope MPS studies [713 consecutive cases with correlating invasive coronary angiography (ICA) and suspected coronary artery disease (CAD) and 468 with low likelihood (LLk) of CAD <5%] were considered. Cases with stenosis <70% by ICA and LLk of CAD were considered normal. Total stress perfusion deficit (TPD) for supine/prone data, stress/rest perfusion change, and transient ischemic dilatation were derived by automated perfusion quantification software and were combined with age, sex, and post-electrocardiogram CAD probability by a boosted ensemble ML algorithm (LogitBoost). The diagnostic accuracy of the model for prediction of obstructive CAD ≥70% was compared to standard prone/supine quantification and to visual analysis by two experienced readers utilizing all imaging, quantitative, and clinical data. Tenfold stratified cross-validation was performed. RESULTS: The diagnostic accuracy of ML (87.3% ± 2.1%) was similar to Expert 1 (86.0% ± 2.1%), but superior to combined supine/prone TPD (82.8% ± 2.2%) and Expert 2 (82.1% ± 2.2%) (P < .01). The receiver operator characteristic areas under curve for ML algorithm (0.94 ± 0.01) were higher than those for TPD and both visual readers (P < .001). The sensitivity of ML algorithm (78.9% ± 4.2%) was similar to TPD (75.6% ± 4.4%) and Expert 1 (76.3% ± 4.3%), but higher than that of Expert 2 (71.1% ± 4.6%), (P < .01). The specificity of ML algorithm (92.1% ± 2.2%) was similar to Expert 1 (91.4% ± 2.2%) and Expert 2 (88.3% ± 2.5%), but higher than TPD (86.8% ± 2.6%), (P < .01). CONCLUSION: ML significantly improves diagnostic performance of MPS by computational integration of quantitative perfusion and clinical data to the level rivaling expert analysis.

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.

Time and event-specific deep learning for personalized risk assessment after cardiac perfusion imaging.

Standard clinical interpretation of myocardial perfusion imaging (MPI) has proven prognostic value for predicting major adverse cardiovascular events (MACE). However, personalizing predictions to a specific event type and time interval is more challenging. We demonstrate an explainable deep learning model that predicts the time-specific risk separately for all-cause death, acute coronary syndrome (ACS), and revascularization directly from MPI and 15 clinical features. We train and test the model internally using 10-fold hold-out cross-validation (n = 20,418) and externally validate it in three separate sites (n = 13,988) with MACE follow-ups for a median of 3.1 years (interquartile range [IQR]: 1.6, 3.6). We evaluate the model using the cumulative dynamic area under receiver operating curve (cAUC). The best model performance in the external cohort is observed for short-term prediction - in the first six months after the scan, mean cAUC for ACS and all-cause death reaches 0.76 (95% confidence interval [CI]: 0.75, 0.77) and 0.78 (95% CI: 0.78, 0.79), respectively. The model outperforms conventional perfusion abnormality measures at all time points for the prediction of death in both internal and external validations, with improvement increasing gradually over time. Individualized patient explanations are visualized using waterfall plots, which highlight the contribution degree and direction for each feature. This approach allows the derivation of individual event probability as a function of time as well as patient- and event-specific risk explanations that may help draw attention to modifiable risk factors. Such a method could help present post-scan risk assessments to the patient and foster shared decision-making.