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.
Extracellular volume (ECV) is a quantitative measure of extracellular compartment expansion, and an increase in ECV is a marker of myocardial fibrosis. Although cardiac magnetic resonance (CMR) is ...considered the standard imaging tool for ECV quantification, cardiac computed tomography (CT) has also been used for ECV assessment.
The aim of this meta-analysis was to evaluate the correlation and agreement in the quantification of myocardial ECV by CT and CMR.
PubMed and Web of Science were searched for relevant publications reporting on the use of CT for ECV quantification compared with CMR as the reference standard. The authors employed a meta-analysis using the restricted maximum-likelihood estimator with a random-effects method to estimate summary correlation and mean difference. A subgroup analysis was performed to compare the correlation and mean differences between single-energy CT (SECT) and dual-energy CT (DECT) techniques for the ECV quantification.
Of 435 papers, 13 studies comprising 383 patients were identified. The mean age range was 57.3 to 82 years, and 65% of patients were male. Overall, there was an excellent correlation between CT-derived ECV and CMR-derived ECV (mean: 0.90 95% CI: 0.86-0.95). The pooled mean difference between CT and CMR was 0.96% (95% CI: 0.14%-1.78%). Seven studies reported correlation values using SECT, and 4 studies reported those using DECT. The pooled correlation from studies utilizing DECT for ECV quantification was significantly higher compared with those with SECT (mean: 0.94 95% CI: 0.91-0.98 vs 0.87 95% CI: 0.80-0.94, respectively; P = 0.01). There was no significant difference in pooled mean differences between SECT vs DECT (P = 0.85).
CT-derived ECV showed an excellent correlation and mean difference of <1% with CMR-derived ECV. However, the overall quality of the included studies was low, and larger, prospective studies are needed to examine the accuracy and diagnostic and prognostic utility of CT-derived ECV.
Display omitted
Controversy exists concerning the relation between diagonal ear lobe crease (DELC) and coronary artery disease (CAD). We examined whether DELC is associated with CAD using coronary computed ...tomography (CT) angiography. We studied 430 consecutive patients without a history of coronary artery intervention who underwent CT angiography on a dual-source scanner. Presence of DELC was agreed by 2 blinded observers. Two blinded readers evaluated CT angiography images for presence of CAD and for significant CAD (≥50% stenosis). Chi-square and t tests were used to assess demographic differences between subgroups with and without DELC and the relation of DELC to 4 measurements of CAD: any CAD, significant CAD, multivessel disease (cutoff ≥2), and number of segments with plaque (cutoff ≥3). Multivariable logistic regression was performed to adjust for CAD confounders: age, gender, symptoms, and CAD risk factors. Mean age was 61 ± 13 and 61% were men. DELC was found in 71%, any CAD in 71%, and significant CAD in 17% of patients. After adjusting for confounders, DELC remained a significant predictor of all 4 measurements of CAD (odds ratio 1.8 to 3.3, p = 0.002 to 0.017). Sensitivity, specificity, and positive and negative predictive values for DELC in detecting any CAD were 78%, 43%, 77%, and 45%. Test accuracy was calculated at 67%. Area under the receiver operator characteristic curve was 61% (p = 0.001). In conclusion, in this study of patients imaged with CT angiography, finding DELC was independently and significantly associated with increased prevalence, extent, and severity of CAD.
It is unknown whether the echocardiographic changes observed after treatment of patients with pulmonary arterial hypertension have prognostic value.
Subjects with pulmonary arterial hypertension, ...confirmed by right heart catheterization, who underwent Doppler echocardiography before (baseline) and after 1 year of treatment (follow-up) with parenteral prostacyclin analogues were retrospectively identified. Echocardiographic parameters were measured offline by two investigators.
A total of 48 patients were included (mean age, 45 ± 14 years; 83% women). Compared with baseline, follow-up echocardiography showed reductions in right atrial area (mean percentage change, 12 ± 25%; P < .001), right ventricular (RV) basal and middle cavity dimensions (mean percentage change, 8.5 ± 14% P < .001 and 6.8 ± 17% P = .005, respectively), and peak tricuspid regurgitant velocity (mean percentage change, 10 ± 14%; P < .001). Tricuspid annular plane systolic excursion (mean percentage change, 36 ± 43%; P < .001) and RV outflow tract time-velocity integral (mean percentage change, 48 ± 66%; P < .001) increased. During a median follow-up period of 52.5 months (interquartile range, 20.5-80 months), 18 patients (37.5%) died, mostly (n = 15 83%) from progression of pulmonary arterial hypertension. The changes in RV end-diastolic area (hazard ratio HR per 10% decrease, 0.73; 95% confidence interval CI, 0.57-0.93), tricuspid valve regurgitation velocity (HR per 10 cm/sec decrease, 0.58; 95% CI, 0.37-0.89), RV outflow tract velocity-time integral (HR per 10% increase, 0.90; 95% CI, 0.83-0.98), and subjective RV function (HR per 1 unit of improvement e.g., from moderate to mild, 0.55; 95% CI, 0.31-0.96) were associated with overall mortality.
Echocardiographic parameters that estimate RV systolic pressure and assess RV morphology and function improve after 1 year of prostacyclin analogue treatment, and the degree of change has prognostic implications.
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.
...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.
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%).
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.
Epicardial fat is a metabolically active fat depot that is strongly associated with obesity, metabolic syndrome, and coronary artery disease (CAD). The relation of epicardial fat to diastolic ...function is unknown. We sought to (1) understand the relation of epicardial fat volume (EFV) to diastolic function and (2) understand the role of EFV in relation to potential risk factors (hypertension, subclinical CAD, and metabolic syndrome) of diastolic dysfunction in apparently healthy subjects with preserved systolic function and no history of CAD. We studied 110 consecutive subjects (65% men, 55 ± 13 years old, mean body mass index 28 ± 5 kg/m2 ) who underwent cardiac computed tomography and transthoracic echocardiography within 6 months as part of a self-referred health screening program. Exclusion criteria included history of CAD, significant valvular disease, systolic dysfunction (left ventricular ejection fraction <50%). Diastolic function was defined according to American Society of Echocardiography guidelines. EFV was measured using validated cardiac computed tomographic software by 2 independent cardiologists blinded to clinical and echocardiographic data. Hypertension and metabolic syndrome were present in 60% and 45%, respectively. Subclinical CAD was identified in 20% of the cohort. Diastolic dysfunction was present in 45 patients. EFV was an independent predictor of diastolic dysfunction, mean peak early diastolic mitral annular velocity, and ratio of early diastolic filling to peak early diastolic mitral annular velocity (p = 0.01, <0.0001, and 0.001, respectively) with incremental contribution to other clinical factors. In conclusion, EFV is an independent predictor of impaired diastolic function in apparently healthy overweight patients even after accounting for associated co-morbidities such as metabolic syndrome, hypertension, and subclinical CAD.
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.
Prior single-center data reported an association between moderate to severe ischemia SPECT-MPI and reduced cardiac death with early revascularization.
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.
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.
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.
Display omitted
Cardiac computed tomography quantification of extracellular volume fraction (CT-ECV) is an emerging biomarker of myocardial fibrosis which has demonstrated high reproducibility, diagnostic and ...prognostic utility. However, there has been wide variation in the CT-ECV protocol in the literature and useful disease cut-offs are yet to be established. The objectives of this meta-analysis were to describe mean CT-ECV estimates and to estimate the effect of CT-ECV protocol parameters on between-study variation.
We conducted a meta-analysis of studies assessing CT-ECV in healthy and diseased participants. We used meta-analytic methods to pool estimates of CT-ECV and performed meta-regression to identify the contribution of protocol parameters to CT-ECV heterogeneity.
Thirteen studies had a total of 248 healthy participants who underwent CT-ECV assessment. Studies of healthy participants had high variation in CT-ECV protocol parameters. The pooled estimate of CT-ECV in healthy participants was 27.6% (95%CI 25.7%–29.4%) with significant heterogeneity (I2 = 93%) compared to 50.2% (95%CI 46.2%–54.2%) in amyloidosis, 31.2% (28.5%–33.8%) in severe aortic stenosis and 36.9% (31.6%–42.3%) in non-ischaemic dilated cardiomyopathies. Meta-regression revealed that CT protocol parameters account for approximately 25% of the heterogeneity in CT-ECV estimates.
CT-ECV estimates for healthy individuals vary widely in the literature and there is significant overlap with estimates in cardiac disease. One quarter of this heterogeneity is explained by differences in CT-ECV protocol parameters. Standardization of CT-ECV protocols is necessary for widespread implementation of CT-ECV assessment for diagnosis and prognosis.
PDF
