Rubidium-82 PET Research Articles

Prognostic value of Transient Ischemic Dilation on Rubidium-82 Positron Emission Tomography Myocardial Perfusion Imaging

RationaleTransient ischemic dilation (TID) of the left ventricular (LV) cavity is considered a high-risk marker in patients with abnormal single photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). Stress image acquisition in Rubidium-82 (82Rb) PET occurs at peak stress compared to 30-60 minutes post stress with SPECT. We aimed to evaluate the prognostic value of TID among patients undergoing 82Rb PET MPI. MethodsA total of 9878 consecutive patients with LVEF ≥40% undergoing rest/pharmacologic stress 82Rb PET MPI from 2010-2016 were followed for a median of 3.2 years. The primary clinical outcome of cardiac death was assessed after adjusting for pre-test risk, known coronary artery disease (CAD), rest left ventricular ejection fraction (LVEF), summed stress score (SSS), LVEF reserve (LVEF-R), myocardial blood flow reserve (MBFR) and early (90-day) revascularization. Pre-specified interactions between TID ratio and SSSwere included to assess potential differences in the prognostic value of TID in patients based on perfusion. ResultsMean age of the cohort was 69.0 (11.7) years, 56.1% female, 49.8% with known CAD, 27.9% with abnormal perfusion (SSS>0).There were 451 cardiac deaths. Higher TID ratio was associated with a significantly higher risk of cardiac death, even after accounting for LVEF-R and MBFR (HR per 0.1 unit increase =1.25 (1.11, 1.41), p<0.001). This was seen both among patients with normal (HR for TID per 0.1 unit increase= 1.24 (95% CI: 1.01, 1.52), p=0.04) and abnormal (HR for TID per 0.1 unit increase= 1.14 (95% CI: 1.02, 1.28), p=0.03) perfusion. ConclusionTID on rest/stress 82RbPET MPI offers independent prognostic value in patients with both normal and abnormal perfusion beyond other risk markers, among patients with LVEF >40%.

Validation of Exponential Dosing for Rubidium-82 PET Imaging in Very Obese Patients

Validation of Exponential Dosing for Rubidium-82 PET Imaging in Very Obese Patients

C-11 | Correlation Between Thermodilution-Derived Coronary Flow Reserve and Rubidium-82 PET Myocardial Flow Reserve in Patients Undergoing Invasive Coronary Function Testing

C-11 | Correlation Between Thermodilution-Derived Coronary Flow Reserve and Rubidium-82 PET Myocardial Flow Reserve in Patients Undergoing Invasive Coronary Function Testing

Machine and deep learning models for accurate detection of ischemia and scar with myocardial blood flow positron emission tomography imaging

BackgroundQuantification of myocardial blood flow (MBF) is used for the noninvasive diagnosis of patients with coronary artery disease (CAD). This study compared traditional statistics, machine learning, and deep learning techniques in their ability to diagnose disease using only the rest and stress MBF values. MethodsThis study included 3245 rest and stress rubidium-82 positron emission tomography (PET) studies and matching diagnostic labels from perfusion reports. Standard logistic regression, lasso logistic regression, support vector machine, random forest, multilayer perceptron, and dense U-Net were compared for per-patient detection and per-vessel localization of scars and ischemia. ResultsReceiver-operator characteristic area under the curve (AUC) of machine learning models was significantly higher than those of traditional statistics models for per-patient detection of disease (0.92–0.95 vs. 0.87) but not for per-vessel localization of ischemia or scar. Random forest showed the highest AUC = 0.95 among the different models compared. On the final hold-out set for generalizability, random forest showed an AUC of 0.92 for detection and 0.89 for localization of perfusion abnormalities. ConclusionsFor per-vessel localization, simple models trained on segmental data performed similarly to a convolutional neural network trained on polar-map data, highlighting the need to justify the use of complex predictive algorithms through comparison with simpler methods.

Quantitative and qualitative comparison of Rubidium-82 and Oxygen-15 water cardiac PET

BackgroundDifferences in tracer characteristics may influence the interpretation of positron emission tomography myocardial perfusion imaging (MPI). We compare the reading of MPIs with a low-extraction retention tracer (82Rb) and a high-extraction non-retention tracer (15O-water) in a selected cohort of patients with known coronary artery disease (CAD). MethodsThirty-nine patients with known CAD referred to 82Rb MPI due to angina underwent rest and stress imaging with both tracers and experienced MPI readers provided blinded consensus reads of all studies. In addition, a comparison of regional and global quantitative measures of perfusion was performed. ResultsThe results showed 74 % agreement in the reading of 82Rb and 15O-water MPI for regional reversible ischemia and global disease, and 82 % agreement for regional irreversible ischemia. The 15O-water MPI identified more cases of global disease (n = 12 (15O-water) vs n = 4 (82Rb), p = 0.03), whereas differences in reversible ischemia (n = 22 vs n = 16, p = 0.11) and, irreversible ischemia (n = 8 vs n = 11, p = 0.45) were not significant. The correlation between myocardial blood flow measured using the two tracers was similar to previous studies (R2 = 0.78) with wide limits of agreement (−0.93 to 0.84 ml/g/min). ConclusionsAgreement between consensus readings of 82Rb and 15O-water MPI was good in patients with known CAD. In this limited size study, no significant differences in the identification of reversible and irreversible ischemia found, whereas 15O-water MPI had a higher positive rate for suspected global disease.

Improved diagnostic accuracy for coronary artery disease detection with quantitative 3D 82Rb PET myocardial perfusion imaging.

To establish requirements for normal databases for quantitative rubidium-82 (82Rb) PET MPI analysis with contemporary 3D PET/CT technology and reconstruction methods for maximizing diagnostic accuracy of total perfusion deficit (TPD), a combined metric of defect extent and severity, versus invasive coronary angiography. In total, 1571 patients with 82Rb PET/CT MPI on a 3D scanner and stress static images reconstructed with and without time-of-flight (TOF) modeling were identified. An additional eighty low pre-test probability of disease (PTP) patients reported as normal were used to form separate sex-stratified and sex-independent iterative and TOF normal databases. 3D normal databases were applied to matched patient reconstructions to quantify TPD. Per-patient and per-vessel performance of 3D versus 2D PET normal databases was assessed with receiver operator characteristic curve analysis. Diagnostic accuracy was evaluated at optimal thresholds established from PTP patients. Results were compared against logistic regression modeling of TPD adjusted for clinical variables, and standard clinical interpretation. TPD diagnostic accuracy was significantly higher using 3D PET normal databases (per-patient: 80.1% for 3D databases, versus 74.9% and 77.7% for 2D database applied to iterative and TOF images respectively, p < 0.05). Differences in male and female normal distributions for 3D attenuation-corrected reconstructions were not clinically meaningful; therefore, sex-independent databases were used. Logistic regression modeling including TPD demonstrated improved performance over clinical reads. Normal databases tailored to 3D PET images provide significantly improved diagnostic accuracy for PET MPI evaluation with automated quantitative TPD. Clinical application of these techniques should be considered to support accurate image interpretation.

Machine learning based model to diagnose obstructive coronary artery disease using calcium scoring, PET imaging, and clinical data

IntroductionAccurate risk stratification in patients with suspected stable coronary artery disease is essential for choosing an appropriate treatment strategy. Our aim was to develop and validate a machine learning (ML) based model to diagnose obstructive CAD (oCAD). MethodWe retrospectively have included 1007 patients without a prior history of CAD who underwent CT-based calcium scoring (CACS) and a Rubidium-82 PET scan. The entire dataset was split 4:1 into a training and test dataset. An ML model was developed on the training set using fivefold stratified cross-validation. The test dataset was used to compare the performance of expert readers to the model. The primary endpoint was oCAD on invasive coronary angiography (ICA). ResultsROC curve analysis showed an AUC of 0.92 (95% CI 0.90-0.94) for the training dataset and 0.89 (95% CI 0.84-0.93) for the test dataset. The ML model showed no significant differences as compared to the expert readers (p ≥ 0.03) in accuracy (89% vs. 88%), sensitivity (68% vs. 69%), and specificity (92% vs. 90%). ConclusionThe ML model resulted in a similar diagnostic performance as compared to expert readers, and may be deployed as a risk stratification tool for obstructive CAD. This study showed that utilization of ML is promising in the diagnosis of obstructive CAD.

Automated dynamic motion correction improves repeatability and reproducibility of myocardial blood flow quantification with rubidium-82 PET imaging

BackgroundPatient motion reduces the accuracy of PET myocardial blood flow (MBF) measurements. This study evaluated the effect of automatic motion correction on test-retest repeatability and inter-observer variability in a clinically relevant population. MethodsPatients with known or suspected CAD underwent repeat rest 82Rb PET scans within minutes as part of their scheduled rest-stress perfusion study. Two trained observers evaluated the presence of heart motion in each scan. Global LV and per-vessel MBF were computed from the dynamic rest images before and after automatic motion correction. Test-retest and inter-observer variability were assessed using intra-class correlation and Bland-Altman analysis. Results140 pairs of test-retest scans were included, with visual motion noted in 18%. Motion correction decreased the global MBF values by 3.5% (0.80 ± 0.24 vs 0.82 ± 0.25 mL⋅min−1⋅g−1; P < 0.001) suggesting that the blood input function was underestimated in cases with patient motion. Test-retest repeatability of global MBF improved by 9.7% (0.25 vs 0.28 mL⋅min−1⋅g−1; P < 0.001) and inter-observer repeatability was improved by 7.1% (0.073 vs 0.079 mL⋅min−1⋅g−1; P = 0.012). There was a marked impact on both test-retest repeatability as well as inter-observer repeatability in the LCX territory, with improvements of 16.5% (0.30 vs 0.36 mL⋅min−1⋅g−1; P < 0.0000) and 18.4% (0.13 vs 0.16 mL⋅min−1⋅g−1; P < 0.001), respectively. ConclusionAutomatic motion correction improved test-retest repeatability and reduced differences between observers.

Exponential dosing to standardize myocardial perfusion image quality with rubidium-82 PET

Background82Rb PET is commonly performed using the same injected activity in all patients, resulting in lower image quality in larger patients. This study compared 82Rb dosing with exponential vs proportional functions of body weight on the standardization of myocardial perfusion image (MPI) quality.MethodsTwo sequential cohorts of N = 60 patients were matched by patient weight. Rest and dipyridamole stress 82Rb PET was performed using 0.1 MBq·kg−2 exponential and 9 MBq·kg−1 proportional dosing. MPI scans were compared qualitatively with visual image quality scoring (IQS) and quantitatively using the myocardium-to-blood contrast-to-noise ratio (CNR) and blood background signal-to-noise ratio (SNR) as a function of body weight.ResultsAverage (min–max) patient body weight was 81 ± 18 kg (46–137 kg). Proportional dosing resulted in decreasing CNR, SNR, and visual IQS with increasing body weight (P < 0.05). Exponential dosing eliminated the weight-dependent decreases in these image quality metrics that were observed in the proportional dosing group.Conclusion82Rb PET dosing as an exponential (squared) function of body weight produced consistent stress perfusion image quality over a wide range of patient weights. Dramatically lower doses can be used in lighter patients, with the equivalent population dose shifted toward the heavier patients to standardize diagnostic image quality.

A systemic review of rubidium-82 PET contrasted with 99mTc-MIBI SPECT for imaging coronary artery disease.

99mTc-sestamibi single photon emission tomography (SPECT) method is widely used for imaging coronary artery disease (CAD). 82-Rubidium-PET is an alternative method that can be used to perform the same purpose. This study aims to determine whether 82-Rubidium-PET can offer extra value over 99mTc-sestamibi SPECT in imaging CAD. To achieve the study aim, a systematic review of the literature for the 2 tracers were conducted. The aim of the systemic review was to find every related previous study that corresponded to well-defined scientific criteria. The analysis of the results was restricted to peer-reviewed papers in order to avoid any selective outcome reports. Besides, extra analysis was carried out to curb or avoid any ascertainment bias. The qualified studies selected for this research were then assessed for the risk of bias. Furthermore, the details of the methods were rechecked to ensure that they were comparable, before synthesizing the results. Eighteen original studies were selected and included in the final analysis out of 803 articles identified at the initial research. Overall, the mean value of sensitivity and specificity for diagnosis of CAD was 84.3% and 75.4%, respectively for technetium 99m sestamibi (99mTc-MIBI). On the other hand, for 82-Rubidium-PET, the mean value of sensitivity and specificity for diagnosis of CAD was 81% and 81%, respectively. The accuracy of diagnostics of these imaging modalities was dependent on the radiotracers and stress agent used in these studies, with 99mTc-MIBI achieving the highest diagnostic value. This study concludes that 99mTc-MIBI-SPECT has higher diagnostic value for diagnosing CAD compared to 82-Rubidium-PET. This indicates that 99mTc-MIBI-SPECT is a more valuable technique for predicting CAD. Besides, for the stress agents used to stimulate the heart and increase workload, this research/study recommends the use of adenosine for the SPECT and the use of dipyridamole for positron emission tomography. However, it suggests the need for more systemic and theoretical studies to assess the real value of 82-Rubidium-PET and the value of stress agents.

Abstract 15103: Stratifying Coronary Artery Disease (CAD) GWAS Loci Using Cardiac Perfusion Positron Emission Tomography to Identify Loci for Coronary Microvascular Disease

Introduction: Coronary Microvascular Disease (CMVD), defined as disease of the coronary pre-arterioles, arterioles, and capillaries, accounts for 30-50% of the burden of Ischemic Heart Disease (IHD). CAD GWAS studies have identified more than 235 loci, however, the populations enrolled represent heterogeneous IHD with inclusion criteria that include ischemia without confirmation of obstructive CAD (Ischemia with non-obstructed Coronary Arteries). Hypothesis: We hypothesize that CAD GWAS studies are really IHD GWAS studies and a subset of patients enrolled have CMVD as the etiology of their ischemia. Thus several CAD GWAS loci may be CMVD loci. Here we use quantitative measures of myocardial blood flow (MBF) and MBF reserve (MBFR) from cardiac Perfusion PET studies to stratify known CAD loci for CMVD. Methods: We performed a genomic association study for 235 known CAD loci in 383 samples of European (EUR) and 539 samples of African ancestry (AFR) in the Penn Medicine Biobank using clinical Rubidium-82 PET using REGENIE software. Models were adjusted for age, sex, age 2 , age x sex, 5 principal components, and batch corresponding to phenotype extraction. We examined regions within 250kb of known CAD loci for association with PET-derived MBF and MBFR. Bonferroni corrected P-value &lt; 2.13e-4 was considered significant. Results: We found 40 loci in patients of AFR ancestry and 11 CAD loci in patients of EUR ancestry that were significantly associated with MBFR, including several genes which are known to play a role in microvasculature function and angiogenesis (VEGFa, FLT1, and FGF1). Stress MBF values have been shown to reflect epicardial CAD. We found 28 loci in patients of AFR ancestry and 12 loci in patients of EUR ancestry which were significantly associated with stress MBF and are mostly distinct from loci associated with MBFR. One notable exception is PRDM16 which was highly significant in both phenotypes. Conclusions: Our study sub-stratified variants previously associated with CAD to identify those that may be involved in CMVD. Several genes known to be involved in microvasculature function (VEGFa, FLT1, and FGF1) were putative CMVD genes. PRDM16 was associated with stress MBF and MBFR. This work prioritizes CAD loci for further study of mechanisms of CMVD.

Diagnostic value of regional myocardial flow reserve measurements using Rubidium-82 PET

PurposeVisual assessment of Rubidium (Rb-82) PET myocardial perfusion images is usually combined with global myocardial flow reserve (MFR) measurements. However, small regional blood flow deficits may go unnoticed. Our aim was to compare the diagnostic value of regional with global MFR in the detection of obstructive coronary artery disease (oCAD).MethodsWe retrospectively included 1519 patients referred for rest and regadenoson-induced stress Rb-82 PET/CT without prior history of oCAD. MFR was determined globally, per vessel territory and per myocardial segment and compared using receiver-operating characteristic analysis. Vessel MFR was defined as the lowest MFR of the coronary territories and segmental MFR as the lowest MFR of the 17-segments. The primary endpoint was oCAD on invasive coronary angiography.ResultsThe 148 patients classified as having oCAD had a lower global MFR (median 1.9, interquartile range [1.5–2.4] vs. 2.4 [2.0–2.9]), lower vessel MFR (1.6 [1.2–2.1] vs. 2.2 [1.9–2.6]) and lower segmental MFR (1.3 [ 0.9–1.6] vs. 1.8 [1.5–2.2]) as compared to the non-oCAD patients (p < 0.001). The area under the curve for segmental MFR (0.81) was larger (p ≤ 0.005) than of global MFR (0.74) and vessel MFR (0.78).ConclusionsThe use of regional MFR instead of global MFR is recommended as it improves the diagnostic value of Rb-82 PET in the detection of oCAD.

Effect of temporal sampling protocols on myocardial blood flow measurements using Rubidium-82 PET

BackgroundA variety of temporal sampling protocols is used worldwide to measure myocardial blood flow (MBF). Both the length and number of time frames in these protocols may alter MBF and myocardial flow reserve (MFR) measurements. We aimed to assess the effect of different clinically used temporal sampling protocols on MBF and MFR quantification in Rubidium-82 (Rb-82) PET imaging. MethodsWe retrospectively included 20 patients referred for myocardial perfusion imaging using Rb-82 PET. A literature search was performed to identify appropriate sampling protocols. PET data were reconstructed using 14 selected temporal sampling protocols with time frames of 5-10 seconds in the first-pass phase and 30-120 seconds in the tissue phase. Rest and stress MBF and MFR were calculated for all protocols and compared to the reference protocol with 26 time frames. ResultsMBF measurements differed (P ≤ 0.003) in six (43%) protocols in comparison to the reference protocol, with mean absolute relative differences up to 16% (range 5%-31%). Statistically significant differences were most frequently found for protocols with tissue phase time frames < 90 seconds. MFR did not differ (P ≥ 0.11) for any of the protocols. ConclusionsVarious temporal sampling protocols result in different MBF values using Rb-82 PET. MFR measurements were more robust to different temporal sampling protocols.

Potential use of Rubidium-82 PET to differentiate neoplasms from inflammatory lesion: Case report

Potential use of Rubidium-82 PET to differentiate neoplasms from inflammatory lesion: Case report

Semi-quantitative assessment of ischemia with rubidium-82 PET myocardial perfusion imaging

PurposeSemi-quantitative scores can be used as an adjunct to visual assessment in rubidium-82 positron emission tomography (82Rb PET). The semi-quantitative cut-off values used in 82Rb PET are derived from single-photon emission computed tomography (SPECT). It is unknown whether these cut-off values can be extrapolated to 82Rb PET. We compared the semi-quantitative with the visual assessment of ischemia and determined which summed difference score (SDS) score predicts ischemia best. MethodsWe included 108 patients who underwent 82Rb PET imaging and performed visual and semi-quantitative assessment. A scan with a SDS ≥ 2 and a summed stress score (SSS) ≥ 4 was considered to demonstrate ischemia. We compared the semi-quantitative with the visual assessment. Results41 (38%) Normal scans, and 67 (62%) scans with ischemia and/or an irreversible defect were included. The semi-quantitative assessment showed ischemia more often than the visual assessment (51% vs 29%, P < .001). Patients with a low or intermediate pre-test probability of coronary artery disease (CAD) and a SDS < 4 did not demonstrate ischemia by visual assessment. ConclusionSemi-quantitative assessment in 82Rb PET imaging clearly demonstrates the presence of ischemia. Ischemia is unlikely in patients with low and intermediate pre-test probability of CAD and a SDS < 4.

Body weight-dependent Rubidium-82 activity results in constant image quality in myocardial perfusion imaging with PET

BackgroundClinical practice shows degrading image quality in heavier patients who undergo myocardial perfusion imaging (MPI) with Rubidium-82 (Rb-82) PET when using a fixed tracer activity. Our aim was to derive and validate a patient-specific activity protocol resulting in a constant image quality in PET MPI. MethodsWe included 251 patients who underwent rest MPI with Rb-82 PET (Discovery 670, GE Healthcare). 132 patients were included retrospectively and were scanned using a fixed activity of 740 MBq. The total number of measured prompts was normalized to activity and correlated to body weight, mass per body length and body mass index to find the best predicting parameter. Next, a patient-specific activity was derived and subsequently validated in 119 additional patients. Image quality was scored by three experts on a four-point scale. ResultsBoth image quality and prompts decreased in heavier patients when using a fixed activity (p < .005). Body weight was used to derive a new activity formula: Activity = 8.3 MBq/kg. When applying this formula, both measured prompts and scored image quality became independent of body weight (p > .60). ConclusionAdministrating a Rb-82 activity that linearly depends on body weight resulted in a constant image quality across all patients and is recommended.

Assessment of motion correction in dynamic rubidium-82 cardiac PET with and without frame-by-frame adjustment of attenuation maps for calculation of myocardial blood flow

BackgroundPatient motion during pharmacological stressing can have substantial impact on myocardial blood flow (MBF) estimated from dynamic PET. This work evaluated a motion correction algorithm with and without adjustment of the PET attenuation map. MethodsFrame-by-frame motion correction was performed by three users on 30 rubidium-82 studies. Data were divided equally into three groups of motion severity [mild (M1), moderate (M2) and severe (M3)]. MBF data were compared for non-motion corrected (NC), motion-corrected-only (MC) and with adjustment of the attenuation map (MCAC). Percentage differences of MBF were calculated in the coronary territories and 17-segment polar plots. Polar plots of spill-over were also generated from the data. ResultsMedian differences of 23% were seen in the RCA and 18% for the LAD in the M3 category for MC vs NC images. Differences for MCAC vs MC images were considerably smaller and typically < 10%. Spill-over plots for MC and MCAC were notably more uniform compared with NC images. ConclusionMotion correction for dynamic rubidium data is desirable for future MBF software updates. Adjustment of the PET attenuation map results in only marginal differences and therefore is unlikely to be an essential requirement. Assessing the uniformity of spill-over plots is a useful visual aid for verifying motion correction techniques.

Value of regional myocardial flow measurements using Rubidium-82 PET

Abstract Funding Acknowledgements Type of funding sources: None. Introduction The combination of myocardial blood flow (MBF) measurements using Rubidium-82 (Rb-82) PET and visual assessment of the PET images is increasingly used due to its high diagnostic and prognostic value. Typically, flow measurements are calculated and used for the myocardium as a whole (global). However, small regional flow deficits may go unnoticed when only looking at global flow values. Purpose To compare the diagnostic value of regional and global myocardial flow measurements using Rb-82 PET in the detection of obstructive CAD. Methods We retrospectively included 1034 patients with no history of coronary artery disease (CAD) referred for rest and regadenoson-induced stress Rb-82 PET/CT. MBFs were calculated using Lortie’s one-tissue compartment model. Myocardial flow reserve (MFR) was calculated as the ratio of MBF during stress and rest. Regional flow was determined per vessel and per segment. Vessel MFR was defined as the lowest flow reserve of LAD, LCX and RCA territories and segmental MFR as the lowest flow reserve in all 17 segments. Follow-up data were obtained from medical records. Patients were classified to have obstructive CAD if follow-up included a positive invasive coronary angiography (ICA), percutaneous coronary intervention (PCI), coronary artery bypass grafting (CABG) or all cause death. Receiver-operating characteristic (ROC) analyses were constructed to compare the diagnostic value of global and regional flow values. Results Follow-up was obtained in all 1034 patients and the median follow-up time was 2.1 years. Myocardial flow reserve values were significantly lower (p &amp;lt; 0.001) in the 128 patients classified with obstructive CAD than in the 906 patients without obstructive CAD: global MFR (median 1.9 [interquartile range 1.6-2.4] vs. 2.5 [2.1-2.9]); vessel MFR (1.6 [1.3-2.1] vs. 2.3 [1.9-2.6]); Segmental MFR (1.3 [0.9-1.7] vs. 1.9 [1.6-2.2]). The area under the curve of vessel MFR (0.79 ± 0.02) and segmental MFR (0.81 ± 0.02) were similar but significantly (p &amp;lt; 0.001) larger than the area of global MFR (0.75 ± 0.03), as shown in the Figure. Conclusion The diagnostic value improved with the use of regional MFR instead of global MFR measurements in the detection of obstructive CAD. Therefore, it seems that visual assessment of PET images can best be combined with regional flow measurements either on a per vessel or a per segment basis in Rubidium-82 PET myocardial perfusion imaging.

Prediction of obstructive coronary artery disease after Rb-82 PET myocardial perfusion imaging and coronary artery calcium scoring using machine learning

Abstract Funding Acknowledgements Type of funding sources: None. Background Accurate risk stratification in patients with suspected stable coronary artery disease (CAD) is essential for choosing an appropriate treatment strategy but remains challenging in clinical practice. Purpose Our aim was to develop and validate a risk model to predict the presence of obstructive CAD after Rubidium-82 PET and a coronary artery calcium score (CACS) scan using a machine learning (ML) algorithm. Methods We retrospectively included 1007 patients without prior cardiovascular history and a low-intermediate pre-test likelihood, referred for rest and regadenoson-induced stress Rubidium-82 PET combined with a CACS scan. Multiple features were included in the ML model; PET derived features such as summed difference score and flow values, CACS, cardiovascular risk factors (cigarette smoking, hypertension, hypercholesterolemia, diabetes, positive family history of CAD), medication; age; gender; body mass index; creatinine serum values; and visual PET interpretation. An XGBoost ML algorithm was developed using a subset of 805 patients to predict obstructive CAD by using 5-fold cross validation in combination with a grid search. Obstructive CAD during follow-up was defined as a significant stenosis during invasive coronary angiography, a percutaneous coronary intervention or a coronary artery bypass graft procedure. The ML algorithm was validated with unseen data of the remaining 202 patients. Results Application of the XGBoost algorithm resulted in an area under the curve (AUC) of 0.93 using the training data (n = 805) and an AUC of 0.89 using the unseen data (n = 202) in predicting obstructive CAD. The strongest predictors were the CAC-scores and quantitative PET derived features. The classical risk factors and medication hardly provided an added value in the prediction of obstructive CAD. Conclusion The developed ML algorithm is able to provide individualized risk stratification by predicting the probability of obstructive CAD. Although validation with a larger dataset could result in a more well defined performance range, this model already shows potential to be implemented in the diagnostic workflow.

Value of coronary artery calcium score in reporting SPECT versus PET myocardial perfusion imaging

Abstract Funding Acknowledgements Type of funding sources: None. Background Although it is well known that coronary artery calcium score (CACS) adds value to reporting myocardial perfusion imaging (MPI) SPECT, its added value to reporting PET MPI is not clear. Purpose Hence, our aim was determine the value of adding CACS in the assessment of PET MPI and SPECT MPI and compare the value between both modalities in a low-risk population. Methods We retrospectively included 412 patients, half of them underwent SPECT with CACS and half underwent Rubidium-82 PET with CACS. We created comparable groups using propensity matching, where the PET group was 1:1 matched to a comparable SPECT group, obtained from a large cohort of 4018. Next, we created two types of image sets for the 412 included patients: MPI-only and MPI + CACS. Two experienced physicians interpreted the 824 images as normal, equivocal or abnormal for ischemia or irreversible defects and were blinded for the used modality. In addition, annualized event rates, defined as the occurrence of all-cause death, non-fatal myocardial infarction or revascularization therapy (PCI or CABG), were compared between the PET and SPECT groups using a follow-up period of 30 months. Results The percentage of scans interpreted as normal was 8% higher with PET-only than with SPECT-only (89 vs 80%, respectively, p = 0.014). Adding CACS to SPECT increased the percentage of scans interpreted as normal from 80% to 86% (p = 0.014), whereas this effect was absent for PET (p = 0.77). Adding CACS reduced the frequency of equivocal scans from 12% and 6% to 0% for both SPECT and PET, respectively. Furthermore, adding CACS resulted in 5% more abnormal interpreted scans for both PET (4.9 to 10%, p = 0.003) and SPECT (8.7 to 14%, p = 0.04). The annualized event rate was 2.7% for the SPECT and 3.5% for the PET group (p = 0.58). The annualized event rates for images interpreted as normal were comparable between all four types of image sets and varied between 0.7-2.0% (p &amp;gt; 0.084). The annualized event rate for equivocal and abnormal scans was higher for PET-only (23%) compared to SPECT-only (4.8%, p &amp;lt; 0.001). Moreover, the event rate for equivocal and abnormal SPECT + CACS (8.6%) was also higher than for SPECT-only (4.8%, p = 0.04), whereas this difference was absent for PET (p = 0.07). Conclusion Adding CACS increases the percentage of scans interpreted as normal for SPECT MPI while the event rate remained unchanged. Adding CACS to PET did not influence the percentage of scans interpreted as normal, limiting the effect of adding CACS to PET in a low-risk population.