Fluorine-18 flurpiridaz is a novel positron emission tomography (PET) myocardial perfusion imaging tracer.
This study sought to assess the diagnostic efficacy of flurpiridaz PET versus ...technetium-99m–labeled single photon emission computed tomography SPECT for the detection and evaluation of coronary artery disease (CAD), defined as ≥50% stenosis by quantitative invasive coronary angiography (ICA). Flurpiridaz safety was also evaluated.
In this phase III prospective multicenter clinical study, 795 patients with known or suspected CAD from 72 clinical sites in the United States, Canada, and Finland were enrolled. A total of 755 patients were evaluable, and the mean age was 62.3 ± 9.5 years, 31% were women, 55% had body mass index ≥30 kg/m2, and 71% had pharmacological stress. Patients underwent 1-day rest-stress (pharmacological or exercise) flurpiridaz PET and 1- or 2-day rest-stress Tc-99m–labeled SPECT and ICA. Images were read by 3 experts blinded to clinical and ICA data.
Sensitivity of flurpiridaz PET (for detection of ≥50% stenosis by ICA) was 71.9% (95% confidence interval CI: 67.0% to 76.3%), significantly (p < 0.001) higher than SPECT (53.7% 95% CI: 48.5% to 58.8%), while specificity did not meet the prespecified noninferiority criterion (76.2% 95% CI: 71.8% to 80.1% vs. 86.6% 95% CI: 83.2% to 89.8%; p = NS). Receiver-operating characteristic curve analysis demonstrated superior discrimination of CAD by flurpiridaz PET versus SPECT in the overall population, in women, obese patients, and patients undergoing pharmacological stress testing (p < 0.001 for all). Flurpiridaz PET was superior to SPECT for defect size (p < 0.001), image quality (p < 0.001), diagnostic certainty (p < 0.001), and radiation exposure (6.1 ± 0.4 mSv vs. 13.4 ± 3.2 mSv; p < 0.001). Flurpiridaz PET was safe and well tolerated.
Flurpiridaz PET myocardial perfusion imaging shows promise as a new tracer for CAD detection and assessment of women, obese patients, and patients undergoing pharmacological stress testing. A second phase III Food and Drug Administration trial is ongoing. (A Phase 3 Multi-center Study to Assess PET Imaging of Flurpiridaz F 18 Injection in Patients with CAD; NCT01347710)
Display omitted
The continued high utilization of rest-stress single-photon emission computed tomographic (SPECT) myocardial perfusion imaging (MPI) is supported by its known clinical benefits, established ...reimbursement, and wide availability of cameras and radiopharmaceuticals. However, traditional rest-stress SPECT protocols tend to be lengthy and inefficient, and the prevalence of equivocal studies continues to be a problem. The use of stress-only SPECT protocols in selected patients, and a new generation of ultrafast SPECT cameras have led to improved image quality, reduced dosimetry and shorter, more efficient MPI protocols. The utilization of positron emission tomographic (PET) MPI has been accelerated by the availability of radiopharmaceuticals that can be generated on-site, and by the availability of more PET cameras. Emerging evidence consistently demonstrates that PET provides improved image quality, greater interpretive certainty, higher diagnostic accuracy, lower patient dosimetry, and shorter imaging protocols as compared to SPECT. Importantly, PET imaging allows assessment of left ventricular function at peak-stress, and evaluation of microvascular function through the measurement of absolute myocardial blood flow at rest and at peak-stress. Wider utilization of PET MPI is hindered by a high cost of entry, high on-going costs, and an immature reimbursement structure.
Angiographic severity of coronary artery stenosis has historically been the primary guide to revascularization or medical management of coronary artery disease. However, physiologic severity defined ...by coronary pressure and/or flow has resurged into clinical prominence as a potential, fundamental change from anatomically to physiologically guided management. This review addresses clinical coronary physiology—pressure and flow—as clinical tools for treating patients. We clarify the basic concepts that hold true for whatever technology measures coronary physiology directly and reliably, here focusing on positron emission tomography and its interplay with intracoronary measurements.
Combined analysis of SPECT myocardial perfusion imaging (MPI) performed with a solid-state camera on patients in 2 positions (semiupright, supine) is routinely used to mitigate attenuation artifacts. ...We evaluated the prediction of obstructive disease from combined analysis of semiupright and supine stress MPI by deep learning (DL) as compared with standard combined total perfusion deficit (TPD).
1,160 patients without known coronary artery disease (64% male) were studied. Patients underwent stress
Tc-sestamibi MPI with new-generation solid-state SPECT scanners in 4 different centers. All patients had on-site clinical reads and invasive coronary angiography correlations within 6 mo of MPI. Obstructive disease was defined as at least 70% narrowing of the 3 major coronary arteries and at least 50% for the left main coronary artery. Images were quantified at Cedars-Sinai. The left ventricular myocardium was segmented using standard clinical nuclear cardiology software. The contour placement was verified by an experienced technologist. Combined stress TPD was computed using sex- and camera-specific normal limits. DL was trained using polar distributions of normalized radiotracer counts, hypoperfusion defects, and hypoperfusion severities and was evaluated for prediction of obstructive disease in a novel leave-one-center-out cross-validation procedure equivalent to external validation. During the validation procedure, 4 DL models were trained using data from 3 centers and then evaluated on the 1 center left aside. Predictions for each center were merged to have an overall estimation of the multicenter performance.
718 (62%) patients and 1,272 of 3,480 (37%) arteries had obstructive disease. The area under the receiver operating characteristics curve for prediction of disease on a per-patient and per-vessel basis by DL was higher than for combined TPD (per-patient, 0.81 vs. 0.78; per-vessel, 0.77 vs. 0.73;
< 0.001). With the DL cutoff set to exhibit the same specificity as the standard cutoff for combined TPD, per-patient sensitivity improved from 61.8% (TPD) to 65.6% (DL) (
< 0.05), and per-vessel sensitivity improved from 54.6% (TPD) to 59.1% (DL) (
< 0.01). With the threshold matched to the specificity of a normal clinical read (56.3%), DL had a sensitivity of 84.8%, versus 82.6% for an on-site clinical read (
= 0.3).
DL improves automatic interpretation of MPI as compared with current quantitative methods.
The study evaluated the automatic prediction of obstructive disease from myocardial perfusion imaging (MPI) by deep learning as compared with total perfusion deficit (TPD).
Deep convolutional neural ...networks trained with a large multicenter population may provide improved prediction of per-patient and per-vessel coronary artery disease from single-photon emission computed tomography MPI.
A total of 1,638 patients (67% men) without known coronary artery disease, undergoing stress
Tc-sestamibi or tetrofosmin MPI with new generation solid-state scanners in 9 different sites, with invasive coronary angiography performed within 6 months of MPI, were studied. Obstructive disease was defined as ≥70% narrowing of coronary arteries (≥50% for left main artery). Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. Stress TPD was computed using sex- and camera-specific normal limits. Deep learning was trained using raw and quantitative polar maps and evaluated for prediction of obstructive stenosis in a stratified 10-fold cross-validation procedure.
A total of 1,018 (62%) patients and 1,797 of 4,914 (37%) arteries had obstructive disease. Area under the receiver-operating characteristic curve for disease prediction by deep learning was higher than for TPD (per patient: 0.80 vs. 0.78; per vessel: 0.76 vs. 0.73: p < 0.01). With deep learning threshold set to the same specificity as TPD, per-patient sensitivity improved from 79.8% (TPD) to 82.3% (deep learning) (p < 0.05), and per-vessel sensitivity improved from 64.4% (TPD) to 69.8% (deep learning) (p < 0.01).
Deep learning has the potential to improve automatic interpretation of MPI as compared with current clinical methods.
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.
Artificial intelligence may improve accuracy of myocardial perfusion imaging (MPI) but will likely be implemented as an aid to physician interpretation rather than an autonomous tool. Deep learning ...(DL) has high standalone diagnostic accuracy for obstructive coronary artery disease (CAD), but its influence on physician interpretation is unknown. We assessed whether access to explainable DL predictions improves physician interpretation of MPI.
We selected a representative cohort of patients who underwent MPI with reference invasive coronary angiography. Obstructive CAD, defined as stenosis ≥50% in the left main artery or ≥70% in other coronary segments, was present in half of the patients. We used an explainable DL model (CAD-DL), which was previously developed in a separate population from different sites. Three physicians interpreted studies first with clinical history, stress, and quantitative perfusion, then with all the data plus the DL results. Diagnostic accuracy was assessed using area under the receiver-operating-characteristic curve (AUC).
In total, 240 patients with a median age of 65 y (interquartile range 58-73) were included. The diagnostic accuracy of physician interpretation with CAD-DL (AUC 0.779) was significantly higher than that of physician interpretation without CAD-DL (AUC 0.747,
= 0.003) and stress total perfusion deficit (AUC 0.718,
< 0.001). With matched specificity, CAD-DL had higher sensitivity when operating autonomously compared with readers without DL results (
< 0.001), but not compared with readers interpreting with DL results (
= 0.122). All readers had numerically higher accuracy with CAD-DL, with AUC improvement 0.02-0.05, and interpretation with DL resulted in overall net reclassification improvement of 17.2% (95% CI 9.2%-24.4%,
< 0.001).
Explainable DL predictions lead to meaningful improvements in physician interpretation; however, the improvement varied across the readers, reflecting the acceptance of this new technology. This technique could be implemented as an aid to physician diagnosis, improving the diagnostic accuracy of MPI.