Funding Acknowledgements Type of funding sources: None. Background and purpose Myocardial blood flow (MBF) measurements using PET are increasingly used to guide the management of patients with (suspected) coronary artery disease (CAD). Day-to-day variability of these measurements is poor with a 21% standard deviation or 40% 95%-confidence interval [Reference: JACC Cardiovasc Imaging, 2017;10(5):565]. This limits clinical applicability in diagnosis, risk stratification and follow-up as these all depend on comparison of flow values with fixed cut-off values. We expect that reproducibility can be improved by combining flow measurements with the variation of flow values within the myocardium. As entropy is a measure of variability of the associated distribution, we compared the reproducibility of an entropy-based flow parameter with that of conventional myocardial flow reserve (MFR) measurements. Methods We performed a study using intra-individual comparison in 24 patients who underwent rest and regadenoson-induced stress myocardial perfusion imaging using Rubidium-82 on two different PET systems (PET1: Discovery 690, GE Healthcare, and PET2: Vereos, Philips Healthcare) within 3 weeks. MBF for both rest and stress was calculated using Lortie’s one-tissue compartment model (Corridor4DM, INVIA). MFR (ratio of MBF stress/rest) was determined for the myocardial as a whole (MFRglobal), for the three vascular territories: LAD, LCX and RCA (MFRregional) and for the 17 segments. Next, we calculated Shannon’s entropy to measure the variation of the 17 MFR segmental values. We multiplied Shannon’s entropy by the mean of the MFR segmental values resulting in an entropy-based MFR (MFRentropy). For each patient MFRglobal, MFRregional and MRFentropy were compared between both PET systems. For each of the three parameters the test-retest precision was calculated as the SD of the relative difference between measurements. Results The mean difference in MFR measurements between both cameras did not differ from zero (p > 0.05). Mean values for PET1 were MFRglobal = 2.4, MFRregional = 2.4 (LAD), 2.4 (LCX) and 2.5 (RCA), and MFRentropy = 2.4. For PET2 we found MFRglobal = 2.5, MFRregional = 2.5 (LAD), 2.4 (LCX) and 2.6 (RCA), and MFRentropy = 2.5. Test-retest precision was lower for MFRentropy with 11% compared to that of MFRglobal (21%), MFRregional LAD (22%), MFRregional LCX (23%) and MFRregional RCA (24%) (p < 0.01). Conclusion The reproducibility of myocardial flow reserve measurements using Rubidium-82 PET improved by a factor of 2 when an entropy-based flow parameter instead of global or regional MFR parameters is used. This entropy-based flow-parameter may be used to better discriminate ischemia from non-ischemia and may therefore improve CAD management.

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.

No 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 > 0.084). The annualized event rate for equivocal and abnormal scans was higher for PET-only (23%) compared to SPECT-only (4.8%, p < 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.

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 < 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 < 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.