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.

In the context of myocardial perfusion imaging (MPI) with cardiac magnetic resonance (CMR), there is ongoing debate on the merits of using technically complex acquisition methods to achieve whole-heart spatial coverage, rather than conventional 3-slice acquisition. An adequately powered comparative study is difficult to achieve given the requirement for two separate stress CMR studies in each patient. The aim of this work is to draw relevant conclusions from SPECT MPI by comparing whole-heart versus simulated 3-slice coverage in a large existing dataset. SPECT data from 651 patients with suspected coronary artery disease who underwent invasive angiography were analyzed. A computational approach was designed to model 3-slice MPI by retrospective subsampling of whole- heart data. For both whole-heart and 3-slice approaches, the diagnostic performance and the stress total perfusion deficit (TPD) score-a measure of ischemia extent/severity-were quantified and compared. Diagnostic accuracy for the 3-slice and whole-heart approaches were similar (area under the curve: 0.843 vs. 0.855, respectively; P = 0.07). The majority (54%) of cases missed by 3-slice imaging had primarily apical ischemia. Whole-heart and 3-slice TPD scores were strongly correlated (R² = 0.93, P < 0.001) but 3-slice TPD showed a small yet significant bias compared to whole-heart TPD (- 1.19%; P < 0.0001) and the 95% limits of agreement were relatively wide (- 6.65% to 4.27%). Incomplete ventricular coverage typically acquired in 3-slice CMR MPI does not significantly affect the diagnostic accuracy. However, 3-slice MPI may fail to detect severe apical ischemia and underestimate the extent/severity of perfusion defects. Our results suggest that caution is required when comparing the ischemic burden between 3-slice and whole-heart datasets, and corroborate the need to establish prognostic thresholds specific to each approach.

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.

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.

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.

Combined analysis of SPECT myocardial perfusion imaging (MPI) performed with a solid-state camera on patients in 2 positions (semiupright, supine) is routinely used to mitigate attenuation artifacts. We evaluated the prediction of obstructive disease from combined analysis of semiupright and supine stress MPI by deep learning (DL) as compared with standard combined total perfusion deficit (TPD). Methods: 1,160 patients without known coronary artery disease (64% male) were studied. Patients underwent stress ^99mTc-sestamibi MPI with new-generation solid-state SPECT scanners in 4 different centers. All patients had on-site clinical reads and invasive coronary angiography correlations within 6 mo of MPI. Obstructive disease was defined as at least 70% narrowing of the 3 major coronary arteries and at least 50% for the left main coronary artery. Images were quantified at Cedars-Sinai. The left ventricular myocardium was segmented using standard clinical nuclear cardiology software. The contour placement was verified by an experienced technologist. Combined stress TPD was computed using sex- and camera-specific normal limits. DL was trained using polar distributions of normalized radiotracer counts, hypoperfusion defects, and hypoperfusion severities and was evaluated for prediction of obstructive disease in a novel leave-one-center-out cross-validation procedure equivalent to external validation. During the validation procedure, 4 DL models were trained using data from 3 centers and then evaluated on the 1 center left aside. Predictions for each center were merged to have an overall estimation of the multicenter performance. Results: 718 (62%) patients and 1,272 of 3,480 (37%) arteries had obstructive disease. The area under the receiver operating characteristics curve for prediction of disease on a per-patient and per-vessel basis by DL was higher than for combined TPD (per-patient, 0.81 vs. 0.78; per-vessel, 0.77 vs. 0.73; P < 0.001). With the DL cutoff set to exhibit the same specificity as the standard cutoff for combined TPD, per-patient sensitivity improved from 61.8% (TPD) to 65.6% (DL) (P < 0.05), and per-vessel sensitivity improved from 54.6% (TPD) to 59.1% (DL) (P < 0.01). With the threshold matched to the specificity of a normal clinical read (56.3%), DL had a sensitivity of 84.8%, versus 82.6% for an on-site clinical read (P = 0.3). Conclusion: DL improves automatic interpretation of MPI as compared with current quantitative methods.

Objective

Prevalence and prognostic impact of cardiovascular disease differ between patients with or without diabetes. We aimed to explore differences in the prevalence and prognosis of myocardial ischemia by automated quantification of total perfusion deficit (TPD) among patients with and without diabetes.

Research design and methods

Of 20,418 individuals who underwent single-photon emission computed tomography myocardial perfusion imaging, 2,951 patients with diabetes were matched to 2,951 patients without diabetes based on risk factors using propensity score. TPD was categorized as TPD = 0%, 0% < TPD < 1%, 1% ≤ TPD < 5%, 5% ≤ TPD ≤ 10%, and TPD >10%. Major adverse cardiovascular events (MACE) were defined as a composite of all-cause mortality, myocardial infarction, unstable angina, or late revascularization.

Results

MACE risk was increased in patients with diabetes compared with patients without diabetes at each level of TPD above 0 (P < 0.001 for interaction). In patients with TPD >10%, patients with diabetes had greater than twice the MACE risk compared with patients without diabetes (annualized MACE rate 9.4 [95% CI 6.7-11.6] and 3.9 [95% CI 2.8-5.6], respectively, P < 0.001). Patients with diabetes with even very minimal TPD (0% < TPD < 1%) experienced a higher risk for MACE than those with 0% TPD (hazard ratio 2.05 [95% CI 1.21-3.47], P = 0.007). Patients with diabetes with a TPD of 0.5% had a similar MACE risk as patients without diabetes with a TPD of 8%.

Conclusions

For every level of TPD >0%, even a very minimal deficit of 0% < TPD < 1%, the MACE risk was higher in the patients with diabetes compared with patients without diabetes. Patients with diabetes with minimal ischemia had comparable MACE risk as patients without diabetes with significant ischemia.

OBJECTIVES:The study evaluated the automatic prediction of obstructive disease from myocardial perfusion imaging (MPI) by deep learning as compared with total perfusion deficit (TPD). BACKGROUND:Deep convolutional neural networks trained with a large multicenter population may provide improved prediction of per-patient and per-vessel coronary artery disease from single-photon emission computed tomography MPI. METHODS:A total of 1,638 patients (67% men) without known coronary artery disease, undergoing stress 99mTc-sestamibi or tetrofosmin MPI with new generation solid-state scanners in 9 different sites, with invasive coronary angiography performed within 6 months of MPI, were studied. Obstructive disease was defined as ≥70% narrowing of coronary arteries (≥50% for left main artery). Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. Stress TPD was computed using sex- and camera-specific normal limits. Deep learning was trained using raw and quantitative polar maps and evaluated for prediction of obstructive stenosis in a stratified 10-fold cross-validation procedure. RESULTS:A total of 1,018 (62%) patients and 1,797 of 4,914 (37%) arteries had obstructive disease. Area under the receiver-operating characteristic curve for disease prediction by deep learning was higher than for TPD (per patient: 0.80 vs. 0.78; per vessel: 0.76 vs. 0.73: p < 0.01). With deep learning threshold set to the same specificity as TPD, per-patient sensitivity improved from 79.8% (TPD) to 82.3% (deep learning) (p < 0.05), and per-vessel sensitivity improved from 64.4% (TPD) to 69.8% (deep learning) (p < 0.01). CONCLUSIONS:Deep learning has the potential to improve automatic interpretation of MPI as compared with current clinical methods.

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.