Dedicated cardiac SPECT scanners with cadmium-zinc-telluride cameras have shown capabilities for shortened scan times or reduced radiation doses, as well as improved image quality. Since most dedicated scanners do not have integrated CT, image quantification with attenuation correction (AC) is challenging and artifacts are routinely encountered in daily clinical practice. In this work, we demonstrated a direct AC technique using deep learning (DL) for myocardial perfusion imaging (MPI). Methods: In an institutional review board-approved retrospective study, 100 cardiac SPECT/CT datasets with ^99mTc-tetrofosmin, obtained using a scanner specifically with a small field of view, were collected at the Yale New Haven Hospital. A convolutional neural network was used for generating DL-based attenuation-corrected SPECT (SPECT_DL) directly from noncorrected SPECT (SPECT_NC) without undergoing an additional image reconstruction step. The accuracy of SPECT_DL was evaluated by voxelwise and segmentwise analyses against the reference, CT-based AC (SPECT_CTAC), using the 17-segment myocardial model of the American Heart Association. Polar maps of representative (best, median, and worst) cases were visually compared to illustrate potential benefits and pitfalls of the DL approach. Results: The voxelwise correlations with SPECT_CTAC were 92.2% ± 3.7% (slope, 0.87; R² = 0.81) and 97.7% ± 1.8% (slope, 0.94; R² = 0.91) for SPECT_NC and SPECT_DL, respectively. The segmental errors of SPECT_NC scattered from -35% to 21% (P < 0.001), whereas the errors of SPECT_DL stayed mostly within ±10% (P < 0.001). The average segmental errors (mean ± SD) were -6.11% ± 8.06% and 0.49% ± 4.35% for SPECT_NC and SPECT_DL, respectively. The average absolute segmental errors were 7.96% ± 6.23% and 3.31% ± 2.87% for SPECT_NC and SPECT_DL, respectively. Review of polar maps revealed successful reduction of attenuation artifacts; however, the performance of SPECT_DL was not consistent for all subjects, likely because of different amounts of attenuation and different uptake patterns. Conclusion: We demonstrated the feasibility of direct AC using DL for SPECT MPI. Overall, our DL approach reduced attenuation artifacts substantially compared with SPECT_NC, justifying further studies to establish safety and consistency for clinical applications in stand-alone SPECT systems suffering from attenuation artifacts.

Aims

Coronary artery disease is frequently diagnosed following evaluation of stable chest pain with anatomical or functional testing. A more granular understanding of patient phenotypes that benefit from either strategy may enable personalized testing.

Methods and results

Using participant-level data from 9572 patients undergoing anatomical (n = 4734) vs. functional (n = 4838) testing in the PROMISE (PROspective Multicenter Imaging Study for Evaluation of Chest Pain) trial, we created a topological representation of the study population based on 57 pre-randomization variables. Within each patient's 5% topological neighbourhood, Cox regression models provided individual patient-centred hazard ratios for major adverse cardiovascular events and revealed marked heterogeneity across the phenomap [median 1.11 (10th to 90th percentile: 0.52-2.61]), suggestive of distinct phenotypic neighbourhoods favouring anatomical or functional testing. Based on this risk phenomap, we employed an extreme gradient boosting algorithm in 80% of the PROMISE population to predict the personalized benefit of anatomical vs. functional testing using 12 model-derived, routinely collected variables and created a decision support tool named ASSIST (Anatomical vs. Stress teSting decIsion Support Tool). In both the remaining 20% of PROMISE and an external validation set consisting of patients from SCOT-HEART (Scottish COmputed Tomography of the HEART Trial) undergoing anatomical-first vs. functional-first assessment, the testing strategy recommended by ASSIST was associated with a significantly lower incidence of each study's primary endpoint (P = 0.0024 and P = 0.0321 for interaction, respectively), as well as a harmonized endpoint of all-cause mortality or non-fatal myocardial infarction (P = 0.0309 and P < 0.0001 for interaction, respectively).

Conclusion

We propose a novel phenomapping-derived decision support tool to standardize the selection of anatomical vs. functional testing in the evaluation of stable chest pain, validated in two large and geographically diverse clinical trial populations.

Attenuation correction (AC) is important for accurate interpretation of SPECT myocardial perfusion imaging (MPI). However, it is challenging to perform AC in dedicated cardiac systems not equipped with a transmission imaging capability. Previously, we demonstrated the feasibility of generating attenuation-corrected SPECT images using a deep learning technique (SPECT_DL) directly from non-corrected images (SPECT_NC). However, we observed performance variability across patients which is an important factor for clinical translation of the technique. In this study, we investigate the feasibility of overcoming the performance variability across patients for the direct AC in SPECT MPI by proposing to develop an advanced network and a data management strategy. To investigate, we compared the accuracy of the SPECT_DL for the conventional U-Net and Wasserstein cycle GAN (WCycleGAN) networks. To manage the training data, clustering was applied to a representation of data in the lower-dimensional space, and the training data were chosen based on the similarity of data in this space. Quantitative analysis demonstrated that DL model with an advanced network improves the global performance for the AC task with the limited data. However, the regional results were not improved. The proposed data management strategy demonstrated that the clustered training has potential benefit for effective training.

Attenuation correction (AC) is important for an accurate interpretation and quantitative analysis of SPECT myocardial perfusion imaging. Dedicated cardiac SPECT systems have invaluable efficacy in the evaluation and risk stratification of patients with known or suspected cardiovascular disease. However, most dedicated cardiac SPECT systems are standalone, not combined with a transmission imaging capability such as computed tomography (CT) for generating attenuation maps for AC. To address this problem, we propose to apply a conditional generative adversarial network (cGAN) for generating attenuation-corrected SPECT images (SPECT_GAN ) directly from non-corrected SPECT images (SPECT_NC ) in image domain as a one-step process without requiring additional intermediate step. The proposed network was trained and tested for 100 cardiac SPECT/CT data from a GE Discovery NM 570c SPECT/CT, collected retrospectively at Yale New Haven Hospital.The generated images were evaluated quantitatively through the normalized root mean square error (NRMSE), peak signal to noise ratio (PSNR), and structural similarity index (SSIM) and statistically through joint histogram and error maps. In comparison to the reference CT-based correction (SPECT_CTAC ), NRMSEs were 0.2258±0.0777 and 0.1410±0.0768 (37.5% reduction of errors); PSNRs 31.7712±2.9965 and 36.3823±3.7424 (14.5% improvement in signal to noise ratio); SSIMs 0.9877±0.0075 and 0.9949±0.0043 (0.7% improvement in structural similarity) for SPECT_NC and SPECT_GAN , respectively. This work demonstrates that the conditional adversarial training can achieve accurate CT-less attenuation correction for SPECT MPI, that is quantitatively comparable to CTAC. Standalone dedicated cardiac SPECT scanners can benefit from the proposed GAN to reduce attenuation artifacts efficiently.

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.