Abstract
Aims
Positron emission tomography (PET) myocardial perfusion imaging (MPI) can non-invasively measure myocardial blood flow reserve (MBFR). We aimed to examine whether MBFR identifies ...patients with a survival benefit after revascularization, helping to guide post-test management.
Methods and results
We examined all-cause mortality in 12 594 consecutive patients undergoing Rb82 rest/stress PET MPI from January 2010 to December 2016, after excluding those with cardiomyopathy, prior coronary artery bypass surgery (CABG), and missing MBFR. Myocardial blood flow reserve was calculated as the ratio of stress to rest absolute myocardial blood flow. A Cox model adjusted for patient and test characteristics, early revascularization (percutaneous coronary intervention or CABG ≤90 days of MPI), and the interaction between MBFR and early revascularization was developed to identify predictors of all-cause mortality. After a median follow-up of 3.2 years, 897 patients (7.1%) underwent early revascularization and 1699 patients (13.5%) died. Ischaemia was present in 4051 (32.3%) patients, with 1413 (11.2%) having ≥10% ischaemia. Mean MBFR was 2.0 ± 1.3, with MBFR <1.8 in 4836 (38.5%). After multivariable adjustment, every 0.1 unit decrease in MBFR was associated with 9% greater hazard of all-cause death (hazard ratio 1.09, 95% confidence interval 1.08–1.10; P < 0.001). There was a significant interaction between MBFR and early revascularization (P < 0.001); such that patients with MBFR ≤1.8 had a survival benefit with early revascularization, regardless of type of revascularization or level of ischaemia.
Conclusion
Myocardial blood flow reserve on PET MPI is associated with all-cause mortality and can identify patients who receive a survival benefit with early revascularization compared to medical therapy. This may be used to guide revascularization, and prospective validation is needed.
The lack of standardized reporting of the magnitude of ischemia on noninvasive imaging contributes to variability in translating the severity of ischemia across stress imaging modalities. We ...identified the risk of coronary artery disease (CAD) death or myocardial infarction (MI) associated with ≥10% ischemic myocardium on stress nuclear imaging as the risk threshold for stress echocardiography and cardiac magnetic resonance. A narrative review revealed that ≥10% ischemic myocardium on stress nuclear imaging was associated with a median rate of CAD death or MI of 4.9%/year (interquartile range: 3.75% to 5.3%). For stress echocardiography, ≥3 newly dysfunctional segments portend a median rate of CAD death or MI of 4.5%/year (interquartile range: 3.8% to 5.9%). Although imprecisely delineated, moderate-severe ischemia on cardiac magnetic resonance may be indicated by ≥4 of 32 stress perfusion defects or ≥3 dobutamine-induced dysfunctional segments. Risk-based thresholds can define equivalent amounts of ischemia across the stress imaging modalities, which will help to translate a common understanding of patient risk on which to guide subsequent management decisions.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Multi-societal consensus recommendations endorse both planar and single photon emission tomographic (SPECT) image acquisitions for the evaluation of cardiac amyloidosis. However, the correlation ...between planar and SPECT findings and the optimal timing of image acquisitions remain uncertain.
This is an analysis of 109 consecutive patients who underwent technetium pyrophosphate nuclear scintigraphy for the evaluation of cardiac amyloidosis. Patients were imaged at 1 and 3 hours after radiotracer injection using both planar and SPECT/CT, and the correlations between imaging protocols were compared.
In the overall cohort (median age 77 years, 75% male), 33 patients had radiotracer localized to the myocardium on SPECT/CT images. There was strong correlation between 1- and 3-hour planar heart-to-contralateral lung ratios (mean difference 0.07, r = 0.94). However, there was discordance between planar image interpretation (based upon semiquantitative score and H/CL ratio) and myocardial localization of radiotracer on SPECT/CT in 17 patients (16%). The pattern of SPECT/CT uptake was identical at 1 and 3 hours in all cases (32 diffuse, 1 focal).
These data support the recommendation that SPECT/CT should be obtained in addition to planar images when performing nuclear scintigraphy for the detection of cardiac amyloidosis. A 1-hour planar and SPECT/CT protocol appears optimal.
Full text
Available for:
EMUNI, FZAB, GEOZS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NUK, OILJ, PNG, SAZU, SBCE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
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.
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.
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.
Abstract
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).
Objectives We sought to evaluate the accuracy and reproducibility of visual estimation of coronary artery calcium (CAC) from computed tomography attenuation correction (CTAC) scans performed for ...hybrid positron emission tomography (PET)/computed tomography (CT) and single-photon emission computed tomography (SPECT)/CT myocardial perfusion imaging (MPI). Background At the time of MPI, hybrid systems obtain a low-dose, non-electrocardiogram (ECG)-gated CT scan that is used to perform attenuation correction. Utility of this CTAC scan in estimating actual CAC as measured by Agatston score (AS) on standard ECG-gated scans has not been previously studied. Methods A total of 492 patients, from 3 centers, receiving both MPI with CTAC and a standard CAC scan were studied. At each site, experienced readers blinded to AS reviewed CTAC images, visually estimating CAC on a 6-level scale: classifying patients as estimated AS of 0, 1 to 9, 10 to 99, 100 to 300, 400 to 999, or ≥1,000. Agreement between visually estimated coronary artery calcium (VECAC) on CTAC and AS, measured standardly and converted to the same scale, was evaluated, as was inter-reader agreement. Results Although CTAC images are low dose and nongated, a high degree of association was observed between VECAC and AS, with 63% of VECACs in the same category as the AS category and 93% within 1 category. Weighted kappa was 0.89 (95% confidence interval: 0.88 to 0.91, p < 0.0001). High weighted kappa statistics were observed for each site, scanner type, and sex. Readers reported identical scores in 65% of cases and scores within 1 category in 93%. Conclusions CAC can be visually assessed from low-dose CTAC scans with high agreement with AS. CTAC scans should be routinely assessed for VECAC.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Prior studies with single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) have shown a survival benefit with early revascularization in patients with >10% to 12.5% ...ischemic myocardium. The relationship among positron emission tomography (PET)–derived extent of ischemia, early revascularization, and survival is unknown.
The purpose of this study was to evaluate the association among percent ischemia on PET MPI, revascularization, and survival.
A total of 16,029 unique consecutive patients who were undergoing Rubidium-82 rest-stress PET MPI from 2010 to 2016 were included. Patients with known cardiomyopathy and nondiagnostic perfusion results were excluded. Percent ischemic myocardium was estimated from a 17-segment model. Propensity scoring was used to account for nonrandomized referral to early revascularization (90 days of PET). A Cox model was developed, adjusting for propensity scores for early revascularization and percent ischemia, and an interaction between ischemia and early revascularization was tested.
Median follow-up was 3.7 years. Overall, 1,277 (8%) patients underwent early revascularization and 2,493 (15.6%) died (738 cardiac). Nearly 37% of patients (n = 5,902) had ischemia, with 13.5% (n = 2,160) having ≥10%. In propensity-adjusted analyses, there was a significant interaction between ischemia and early revascularization (p < 0.001 for all-cause and cardiac death), such that patients with greater ischemia had improved survival with early revascularization, with a potential ischemia threshold at 5% (upper limit 95% confidence interval at 10%). There was no differential association between ischemia and early revascularization on death based on history of known coronary artery disease (interaction p = 0.72).
In a contemporary cohort of patients undergoing PET MPI, patients with greater ischemia had a survival benefit from early revascularization. On exploratory analyses, this threshold was lower than that previously reported for SPECT. These findings require future validation in prospective cohorts or trials.
Display omitted
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
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.
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.
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).
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.
Full text
Available for:
EMUNI, FZAB, GEOZS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NUK, OILJ, PNG, SAZU, SBCE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ