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.

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.

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.

Simplified quantification of 13N-ammonia PET myocardial blood flow: A comparative study with the standard compartment model to facilitate clinical use.

BACKGROUND: Short imaging protocol to quantify myocardial blood flow (MBF) and myocardial flow reserve (MFR) may enhance the clinical application of 13N-ammonia cardiac PET. We assessed the flow quantitation of 13N-ammonia PET implementing simple retention model and two-compartment model. METHODS: Fourteen healthy volunteers (HVT) and twenty-three clinical patients received 13N-ammonia PET/CT. The simple retention model used the first 7-minute image to quantify MBF. Global and regional MBF and MFR of the two models were compared. RESULTS: Global and regional MBF and MFR of these two models were highly correlated with mildly inferior correlation in RCA territory (global R2: rest MBF = 0.79, stress MBF = 0.65, MFR = 0.77; regional R2: rest MBF ≥ 0.72, stress MBF ≥ 0.52, MFR ≥ 0.68). There were significant differences for MFR (4.04 ± 0.72, 3.66 ± 0.48, p = .02) and rest MBF (0.69 ± 0.12, 0.78 ± 0.12, p = .02) between the two models in the HVT group. CONCLUSIONS: 13N-ammonia global and regional MBF and MFR from the simple retention model demonstrate strong correlations with that from the two-compartment model. Significant differences of MFR and rest MBF are noted in the HVT group, with a proposed normal reference value for the 13N-ammonia short simple retention protocol.

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.

SPECT myocardial blood flow quantitation toward clinical use: a comparative study with 13N-Ammonia PET myocardial blood flow quantitation.

OBJECTIVES: The aim of this study was to evaluate the accuracy of myocardial blood flow (MBF) quantitation of 99mTc-Sestamibi (MIBI) single photon emission computed tomography (SPECT) compared with 13N-Ammonia (NH3) position emission tomography (PET) on the same cohorts. BACKGROUND: Recent advances of SPECT technologies have been applied to develop MBF quantitation as a promising tool to diagnose coronary artery disease (CAD) for areas where PET MBF quantitation is not available. However, whether the SPECT approach can achieve the same level of accuracy as the PET approach for clinical use still needs further investigations. METHODS: Twelve healthy volunteers (HVT) and 16 clinical patients with CAD received both MIBI SPECT and NH3 PET flow scans. Dynamic SPECT images acquired with high temporary resolution were fully corrected for physical factors and processed to quantify K1 using the standard compartmental modeling. Human MIBI tracer extraction fraction (EF) was determined by comparing MIBI K1 and NH3 flow on the HVT group and then used to convert flow values from K1 for all subjects. MIBI and NH3 flow values were systematically compared to validate the SPECT approach. RESULTS: The human MIBI EF was determined as [1.0-0.816*exp(-0.267/MBF)]. Global and regional MBF and myocardial flow reserve (MFR) of MIBI SPECT and NH3 PET were highly correlated for all subjects (global R2: MBF = 0.92, MFR = 0.78; regional R2: MBF ≥ 0.88, MFR ≥ 0.71). No significant differences for rest flow, stress flow, and MFR between these two approaches were observed (All p ≥ 0.088). Bland-Altman plots overall revealed small bias between MIBI SPECT and NH3 PET (global: ΔMBF = -0.03Lml/min/g, ΔMFR = 0.07; regional: ΔMBF = -0.07 - 0.06 , ΔMFR = -0.02 - 0.22). CONCLUSIONS: Quantitation with SPECT technologies can be accurate to measure myocardial blood flow as PET quantitation while comprehensive imaging factors of SPECT to derive the variability between these two approaches were fully addressed and corrected.

Prognostic assessment of 18F-boronophenylalanine positron emission tomography (BPA-PET) in salvage boron neutron capture therapy for malignant brain tumors.

Background: Boron neutron capture therapy (BNCT) stands out as a propitious anti-cancer modality. 18F-boronophenylalanine positron emission tomography (BPA-PET) holds the potential to ascertain the concentration of BPA within the tumor, enabling meticulous treatment planning and outcome evaluation. However, no studies have been conducted on comparing the outcomes of those treated with BNCT to those who did not undergo this therapy. This study endeavors to analyze the correlation between BPA-PET and BNCT in the context of malignant brain tumors, and assess the survival outcomes following BNCT. Methods: A cohort study was performed on patients who underwent BPA-PET between February 2017 and April 2022 in our hospital. Patients were stratified into two groups: those subjected to BNCT (Group 1) and those not (Group 2). The tumor to normal tissue (T/N) ratio derived from BPA-PET was set at 2.5. The findings were scrutinized based on clinical follow-up. Student's t-test and Chi-squared test were employed to discern differences between the groups. A cumulative survival curve was constructed employing the Kaplan-Meier method. Differences were considered statistically significant at P<0.05. Results: In total, 116 patients with T/N ratios obtained from BPA-PET were enrolled. BNCT was administered to 58 patients, while mortality was observed in 100 patients. The median overall survival (OS) for the two groups was 8.5 and 6.0 months, respectively. The cumulative OS exhibited no significant discrepancy between the two groups, nor in their T/N ratios. Within Group 1, 44 out of 58 (75.9%) patients exhibited T/N ratios exceeding 2.5. Excluding 3 patients who expired within 3 months, 55 out of 58 patients were evaluated for response after BNCT. The objective response rate (ORR) was 30.9%. Patients achieving ORR displayed substantially higher survival rates compared to those without (median OS 13.5 vs. 8.3 months, P=0.0021), particularly when T/N ratio exceeded 2.5 (median OS 14.8 vs. 9.0 months, P=0.0199). Conclusions: BNCT does not appear indispensable for prolonging the survival of patients afflicted with malignant brain tumors. Nevertheless, it proves advantageous when ORR is attained, a condition closely linked to the values of T/N ratio derived from BPA-PET.

Survival outcomes of radium-223 therapy for metastatic castration-resistant prostate cancer following national health insurance reimbursement in Taiwan.

BACKGROUND: Radium-223 dichloride (Ra-223) prolongs overall survival (OS) in metastatic castration-resistant prostate cancer (mCRPC) with symptomatic bone metastases. However, there is considerable variation in outcomes among individuals. We aimed to evaluate the prognostic determinants associated with patient survival following National Health Insurance (NHI) reimbursement for Ra-223 therapy in Taiwan. METHODS: Patients with mCRPC who underwent Ra-223 treatment at Taipei Veterans General Hospital were retrospectively enrolled. Each intravenous Ra-223 dose was administered at 55 kBq/kg at 4-week intervals. Clinical outcomes were obtained from medical records; potential prognostic factors for survival were assessed. Kaplan-Meier analysis was used to generate cumulative survival curves; between-group differences were evaluated using the Chi-squared test. Statistical significance was set at p < 0.05. RESULTS: Seventy-six patients underwent Ra-223 therapy; 62 patients received NHI reimbursement and the remainder self-paid. Fifty patients (65.8%) completed six cycles of treatment; 26 (34.2%) received 1 to 5 cycles. Mortality occurred in 47 patients. Factors significantly associated with survival included ≤five bone metastases ( p = 0.0018), baseline prostate-specific antigen (PSA) ≤36 ng/mL ( p = 0.0004), baseline alkaline phosphate (ALP) <115 U/L ( p = 0.0007), and baseline hemoglobin (Hb) >12 g/dL ( p = 0.0029). Patients who completed six cycles of treatment achieved significantly higher OS compared to those who did not ( p < 0.0001). There has been a 4.4-fold increase in the number of patients since reimbursement began; there was no significant difference in OS between patients who received NHI reimbursement and those who self-paid. CONCLUSION: Administration of Ra-223 demonstrates considerable potential to extend the survival of patients with mCRPC. Survival outcomes may be influenced by various prognostic factors. However, no significant difference in OS was observed subsequent to reimbursement of Ra-223 therapy for mCRPC through the NHI system in Taiwan.

Hyperphosphatemia-Related False-Positive 99m Tc-Pyrophosphate Myocardial Scan: A Case Report With Endomyocardial Biopsy Result.

ABSTRACT: With documented high specificity, 99m Tc-pyrophosphate (PYP) scan enables the diagnosis of transthyretin cardiomyopathy to be made reliably without endomyocardial biopsy in patients who do not have monoclonal gammopathy. We report a case with extensive myocardial uptake of Perugini 3 score in the 3-hour 99m Tc-PYP myocardial SPECT that suggested transthyretin cardiac amyloidosis. However, a followed endomyocardial biopsy revealed no amyloid deposition. In this case, hyperphosphatemia was the most likely and presumptive cause of the false-positive 99m Tc-PYP scan. With this case, our experiences of the potential causes of false-positive results of 99m Tc-PYP are further expanded.

Follow-up Tc-99 m pyrophosphate cardiac scan for patients with transthyretin cardiac amyloidosis treated with tafamidis.

BACKGROUND: Tafamidis has been used for treatment of transthyretin cardiac amyloidosis (ATTR-CA). However, Tc-99 m pyrophosphate (PYP) cardiac scan for follow-up after tafamidis therapy has not been reported. METHODS: From May 2017 to March 2022, five patients with or without tafamidis therapy had received two Tc-99 m PYP cardiac scans. Tc-99 m PYP cardiac scan was performed with planar image and single photon emission computed tomography/computed tomography (SPECT/CT) 3 h after administration of Tc-99 m PYP. Perugini grading system was applied to determine positive or negative result of the scan. Heart to contralateral lung (H/CL) ratio as well as the difference of H/CL ratio between first and second Tc-99 m PYP cardiac scans (ΔH/CL ratio) was calculated. RESULTS: In the five patients participated in this study, three received tafamidis therapy and H/CL ratio was significantly decreased (p = 0.02) after tafamidis therapy. Besides, the ΔH/CL ratio was larger in patients with tafamidis therapy than that in those without tafamidis therapy, albeit not reaching statistical significance (p = 0.2). CONCLUSION: A decrease in H/CL ratio was found after tafamidis therapy in patients with ATTR-CA, albeit the magnitude of changes in the H/CL ratio (ΔH/CL ratio) was not significantly different from that of patients without tafamidis therapy. Future study with larger population might be required to further clarify the effect of tafamidis therapy on myocardial uptake of Tc-99 m PYP. CLINICAL TRIAL REGISTRATION: No clinical trial was conducted in our retrospective study.

Differences in Prognostic Value of Myocardial Perfusion Single-Photon Emission Computed Tomography Using High-Efficiency Solid-State Detector Between Men and Women in a Large International Multicenter Study.

BACKGROUND: Semiquantitative assessment of stress myocardial perfusion defect has been shown to have greater prognostic value for prediction of major adverse cardiac events (MACE) in women compared with men in single-center studies with conventional single-photon emission computed tomography (SPECT) cameras. We evaluated sex-specific difference in the prognostic value of automated quantification of ischemic total perfusion defect (ITPD) and the interaction between sex and ITPD using high-efficiency SPECT cameras with solid-state detectors in an international multicenter imaging registry (REFINE SPECT [Registry of Fast Myocardial Perfusion Imaging With Next-Generation SPECT]). METHODS: Rest and exercise or pharmacological stress SPECT myocardial perfusion imaging were performed in 17 833 patients from 5 centers. MACE was defined as the first occurrence of death or myocardial infarction. Total perfusion defect (TPD) at rest, stress, and ejection fraction were quantified automatically by software. ITPD was given by stressTPD-restTPD. Cox proportional hazards model was used to evaluate the association between ITPD versus MACE-free survival and expressed as a hazard ratio. RESULTS: In 10614 men and 7219 women, with a median follow-up of 4.75 years (interquartile range, 3.7-6.1), there were 1709 MACE. In a multivariable Cox model, after adjusting for revascularization and other confounding variables, ITPD was associated with MACE (hazard ratio, 1.08 [95% CI, 1.05-1.1]; P<0.001). There was an interaction between ITPD and sex (P<0.001); predicted survival for ITPD<5% was worse among men compared to women, whereas survival among women was worse than men for ITPD≥5%, P<0.001. CONCLUSIONS: In the international, multicenter REFINE SPECT registry, moderate and severe ischemia as quantified by ITPD from high-efficiency SPECT is associated with a worse prognosis in women compared with men.

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.

Prognostically safe stress-only single-photon emission computed tomography myocardial perfusion imaging guided by machine learning: report from REFINE SPECT.

AIMS: Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) stress-only protocols reduce radiation exposure and cost but require clinicians to make immediate decisions regarding rest scan cancellation. We developed a machine learning (ML) approach for automatic rest scan cancellation and evaluated its prognostic safety. METHODS AND RESULTS: In total, 20 414 patients from a solid-state SPECT MPI international multicentre registry with clinical data and follow-up for major adverse cardiac events (MACE) were used to train ML for MACE prediction as a continuous probability (ML score), using 10-fold repeated hold-out testing to separate test from training data. Three ML score thresholds (ML1, ML2, and ML3) were derived by matching the cancellation rates achieved by physician interpretation and two clinical selection rules. Annual MACE rates were compared in patients selected for rest scan cancellation between approaches. Patients selected for rest scan cancellation with ML had lower annualized MACE rates than those selected by physician interpretation or clinical selection rules (ML1 vs. physician interpretation: 1.4 ± 0.1% vs. 2.1 ± 0.1%; ML2 vs. clinical selection: 1.5 ± 0.1% vs. 2.0 ± 0.1%; ML3 vs. stringent clinical selection: 0.6 ± 0.1% vs. 1.7 ± 0.1%, all P < 0.0001) at matched cancellation rates (60 ± 0.7, 64 ± 0.7, and 30 ± 0.6%). Annualized all-cause mortality rates in populations recommended for rest cancellation by physician interpretation, clinical selection approaches were higher (1.3%, 1.2%, and 1.0%, respectively) compared with corresponding ML thresholds (0.6%, 0.6%, and 0.2%). CONCLUSION: ML, using clinical and stress imaging data, can be used to automatically recommend cancellation of rest SPECT MPI scans, while ensuring higher prognostic safety than current clinical approaches.

Impact of Early Revascularization on Major Adverse Cardiovascular Events in Relation to Automatically Quantified Ischemia.

OBJECTIVES: Using a contemporary, multicenter international single-photon emission computed tomography myocardial perfusion imaging (SPECT-MPI) registry, this study characterized the potential major adverse cardiovascular event(s) (MACE) benefit of early revascularization based on automatic quantification of ischemia. BACKGROUND: Prior single-center data reported an association between moderate to severe ischemia SPECT-MPI and reduced cardiac death with early revascularization. METHODS: Consecutive patients from a multicenter, international registry who underwent 99mTc SPECT-MPI between 2009 and 2014 with solid-state scanners were included. Ischemia was quantified automatically as ischemic total perfusion deficit (TPD). Early revascularization was defined as within 90 days. The primary outcome was MACE (death, myocardial infarction, and unstable angina). A propensity score was developed to adjust for nonrandomization of revascularization; then, multivariable Cox modeling adjusted for propensity score and demographics was used to predict MACE. RESULTS: In total, 19,088 patients were included, with a mean follow-up of 4.7 ± 1.6 years, during which MACE occurred in 1,836 (9.6%) patients. There was a significant interaction between ischemic TPD modeled as a continuous variable and early revascularization (interaction p value: 0.012). In this model, there was a trend toward reduced MACE in patients with >5.4% ischemic TPD and a significant association with reduced MACE in patients with >10.2% ischemic TPD. CONCLUSIONS: In this large, international, multicenter study reflecting contemporary cardiology practice, early revascularization of patients with >10.2% ischemia on SPECT-MPI, quantified automatically, was associated with reduced MACE.

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.

Machine learning predicts per-vessel early coronary revascularization after fast myocardial perfusion SPECT: results from multicentre REFINE SPECT registry.

AIMS: To optimize per-vessel prediction of early coronary revascularization (ECR) within 90 days after fast single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) using machine learning (ML) and introduce a method for a patient-specific explanation of ML results in a clinical setting. METHODS AND RESULTS: A total of 1980 patients with suspected coronary artery disease (CAD) underwent stress/rest 99mTc-sestamibi/tetrofosmin MPI with new-generation SPECT scanners were included. All patients had invasive coronary angiography within 6 months after SPECT MPI. ML utilized 18 clinical, 9 stress test, and 28 imaging variables to predict per-vessel and per-patient ECR with 10-fold cross-validation. Area under the receiver operator characteristics curve (AUC) of ML was compared with standard quantitative analysis [total perfusion deficit (TPD)] and expert interpretation. ECR was performed in 958 patients (48%). Per-vessel, the AUC of ECR prediction by ML (AUC 0.79, 95% confidence interval (CI) [0.77, 0.80]) was higher than by regional stress TPD (0.71, [0.70, 0.73]), combined-view stress TPD (AUC 0.71, 95% CI [0.69, 0.72]), or ischaemic TPD (AUC 0.72, 95% CI [0.71, 0.74]), all P < 0.001. Per-patient, the AUC of ECR prediction by ML (AUC 0.81, 95% CI [0.79, 0.83]) was higher than that of stress TPD, combined-view TPD, and ischaemic TPD, all P < 0.001. ML also outperformed nuclear cardiologists' expert interpretation of MPI for the prediction of early revascularization performance. A method to explain ML prediction for an individual patient was also developed. CONCLUSION: In patients with suspected CAD, the prediction of ECR by ML outperformed automatic MPI quantitation by TPDs (per-vessel and per-patient) or nuclear cardiologists' expert interpretation (per-patient).

5-Year Prognostic Value of Quantitative Versus Visual MPI in Subtle Perfusion Defects: Results From REFINE SPECT.

OBJECTIVES: This study compared the ability of automated myocardial perfusion imaging analysis to predict major adverse cardiac events (MACE) to that of visual analysis. BACKGROUND: Quantitative analysis has not been compared with clinical visual analysis in prognostic studies. METHODS: A total of 19,495 patients from the multicenter REFINE SPECT (REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT) study (64 ± 12 years of age, 56% males) undergoing stress Tc-99m-labeled single-photon emission computed tomography (SPECT) myocardial perfusion imaging were followed for 4.5 ± 1.7 years for MACE. Perfusion abnormalities were assessed visually and categorized as normal, probably normal, equivocal, or abnormal. Stress total perfusion deficit (TPD), quantified automatically, was categorized as TPD = 0%, TPD >0% to <1%, ≤1% to <3%, ≤3% to <5%, ≤5% to ≤10%, or TPD >10%. MACE consisted of death, nonfatal myocardial infarction, unstable angina, or late revascularization (>90 days). Kaplan-Meier and Cox proportional hazards analyses were performed to test the performance of visual and quantitative assessments in predicting MACE. RESULTS: During follow-up examinations, 2,760 (14.2%) MACE occurred. MACE rates increased with worsening of visual assessments, that is, the rate for normal MACE was 2.0%, 3.2% for probably normal, 4.2% for equivocal, and 7.4% for abnormal (all p < 0.001). MACE rates increased with increasing stress TPD from 1.3% for the TPD category of 0% to 7.8% for the TPD category of >10% (p < 0.0001). The adjusted hazard ratio (HR) for MACE increased even in equivocal assessment (HR: 1.56; 95% confidence interval [CI]: 1.37 to 1.78) and in the TPD category of ≤3% to <5% (HR: 1.74; 95% CI: 1.41 to 2.14; all p < 0.001). The rate of MACE in patients visually assessed as normal still increased from 1.3% (TPD = 0%) to 3.4% (TPD ≥5%) (p < 0.0001). CONCLUSIONS: Quantitative analysis allows precise granular risk stratification in comparison to visual reading, even for cases with normal clinical reading.

Myocardial Ischemic Burden and Differences in Prognosis Among Patients With and Without Diabetes: Results From the Multicenter International REFINE SPECT Registry.

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.

Transient ischaemic dilation and post-stress wall motion abnormality increase risk in patients with less than moderate ischaemia: analysis of the REFINE SPECT registry.

AIMS: Ischaemia on single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is strongly associated with cardiovascular risk. Transient ischaemic dilation (TID) and post-stress wall motion abnormalities (WMA) are non-perfusion markers of ischaemia with incremental prognostic utility. Using a large, multicentre SPECT MPI registry, we assessed the degree to which these features increased the risk of major adverse cardiovascular events (MACE) in patients with less than moderate ischaemia. METHODS AND RESULTS: Ischaemia was quantified with total perfusion deficit using semiautomated software and classified as: none (<1%), minimal (1 to <5%), mild (5 to <10%), moderate (10 to <15%), and severe (≥15%). Univariable and multivariable Cox proportional hazard analyses were used to assess associations between high-risk imaging features and MACE. We included 16 578 patients, mean age 64.2 and median follow-up 4.7 years. During follow-up, 1842 patients experienced at least one event. Patients with mild ischaemia and TID were more likely to experience MACE compared with patients without TID [adjusted hazard ratio (HR) 1.42, P = 0.023], with outcomes not significantly different from patients with moderate ischaemia without other high-risk features (unadjusted HR 1.15, P = 0.556). There were similar findings in patients with post-stress WMA. However, in multivariable analysis of patients with mild ischaemia, TID (adjusted HR 1.50, P = 0.037), but not WMA, was independently associated with increased MACE. CONCLUSION: In patients with mild ischaemia, TID or post-stress WMA identify groups of patients with outcomes similar to patients with moderate ischaemia. Whether these combinations identify patients who may derive benefit from revascularization deserves further investigation.