Background: Major uncertainties remain regarding disease activity within the retained native aortic valve, and regarding bioprosthetic valve durability, after transcatheter aortic valve implantation (TAVI). We aimed to assess native aortic valve disease activity and bioprosthetic valve durability in patients with TAVI in comparison with subjects with bioprosthetic surgical aortic valve replacement (SAVR). Methods: In a multicenter cross-sectional observational cohort study, patients with TAVI or bioprosthetic SAVR underwent baseline echocardiography, computed tomography angiography, and ¹⁸ F-sodium fluoride ( ¹⁸ F-NaF) positron emission tomography. Participants (n=47) were imaged once with ¹⁸ F-NaF positron emission tomography/computed tomography either at 1 month (n=9, 19%), 2 years (n=22, 47%), or 5 years (16, 34%) after valve implantation. Patients subsequently underwent serial echocardiography to assess for changes in valve hemodynamic performance (change in peak aortic velocity) and evidence of structural valve dysfunction. Comparisons were made with matched patients with bioprosthetic SAVR (n=51) who had undergone the same imaging protocol. Results: In patients with TAVI, native aortic valves demonstrated ¹⁸ F-NaF uptake around the outside of the bioprostheses that showed a modest correlation with the time from TAVI ( r =0.36, P =0.023). ¹⁸ F-NaF uptake in the bioprosthetic leaflets was comparable between the SAVR and TAVI groups (target-to-background ratio, 1.3 [1.2–1.7] versus 1.3 [1.2–1.5], respectively; P =0.27). The frequencies of imaging evidence of bioprosthetic valve degeneration at baseline were similar on echocardiography (6% versus 8%, respectively; P =0.78), computed tomography (15% versus 14%, respectively; P =0.87), and positron emission tomography (15% versus 29%, respectively; P =0.09). Baseline ¹⁸ F-NaF uptake was associated with a subsequent change in peak aortic velocity for both TAVI ( r =0.7, P <0.001) and SAVR ( r =0.7, P <0.001). On multivariable analysis, ¹⁸ F-NaF uptake was the only predictor of peak velocity progression ( P <0.001). Conclusions: In patients with TAVI, native aortic valves demonstrate evidence of ongoing active disease. Across imaging modalities, TAVI degeneration is of similar magnitude to bioprosthetic SAVR, suggesting comparable midterm durability. Registration: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT02304276.

Background: We aim to develop an explainable deep learning (DL) network for the prediction of all-cause mortality directly from positron emission tomography myocardial perfusion imaging flow and perfusion polar map data and evaluate it using prospective testing. Methods: A total of 4735 consecutive patients referred for stress and rest ⁸² Rb positron emission tomography between 2010 and 2018 were followed up for all-cause mortality for 4.15 (2.24–6.3) years. DL network utilized polar maps of stress and rest perfusion, myocardial blood flow, myocardial flow reserve, and spill-over fraction combined with cardiac volumes, singular indices, and sex. Patients scanned from 2010 to 2016 were used for training and validation. The network was tested in a set of 1135 patients scanned from 2017 to 2018 to simulate prospective clinical implementation. Results: In prospective testing, the area under the receiver operating characteristic curve for all-cause mortality prediction by DL (0.82 [95% CI, 0.77–0.86]) was higher than ischemia (0.60 [95% CI, 0.54–0.66]; P <0.001), myocardial flow reserve (0.70 [95% CI, 0.64–0.76], P <0.001) or a comprehensive logistic regression model (0.75 [95% CI, 0.69–0.80], P <0.05). The highest quartile of patients by DL had an annual all-cause mortality rate of 11.87% and had a 16.8 ([95% CI, 6.12%–46.3%]; P <0.001)-fold increase in the risk of death compared with the lowest quartile patients. DL showed a 21.6% overall reclassification improvement as compared with established measures of ischemia. Conclusions: The DL model trained directly on polar maps allows improved patient risk stratification in comparison with established methods for positron emission tomography flow or perfusion assessments.

BACKGROUND: Plaque quantification from coronary computed tomography angiography has emerged as a valuable predictor of cardiovascular risk. Deep learning can provide automated quantification of coronary plaque from computed tomography angiography. We determined per-patient age- and sex-specific distributions of deep learning–based plaque measurements and further evaluated their risk prediction for myocardial infarction in external samples. METHODS: In this international, multicenter study of 2803 patients, a previously validated deep learning system was used to quantify coronary plaque from computed tomography angiography. Age- and sex-specific distributions of coronary plaque volume were determined from 956 patients undergoing computed tomography angiography for stable coronary artery disease from 5 cohorts. Multicenter external samples were used to evaluate associations between coronary plaque percentiles and myocardial infarction. RESULTS: Quantitative deep learning plaque volumes increased with age and were higher in male patients. In the combined external sample (n=1847), patients in the ≥75th percentile of total plaque volume (unadjusted hazard ratio, 2.65 [95% CI, 1.47–4.78]; P =0.001) were at increased risk of myocardial infarction compared with patients below the 50th percentile. Similar relationships were seen for most plaque volumes and persisted in multivariable analyses adjusting for clinical characteristics, coronary artery calcium, stenosis, and plaque volume, with adjusted hazard ratios ranging from 2.38 to 2.50 for patients in the ≥75th percentile of total plaque volume. CONCLUSIONS: Per-patient age- and sex-specific distributions for deep learning–based coronary plaque volumes are strongly predictive of myocardial infarction, with the highest risk seen in patients with coronary plaque volumes in the ≥75th percentile.

Asymmetric wall thickening has been described in patients with aortic stenosis. However, it remains poorly characterized and its prognostic implications are unclear. We hypothesized this pattern of adaptation is associated with advanced remodelling, left ventricular decompenzation, and a poor prognosis. In a prospective observational cohort study, 166 patients with aortic stenosis (age 69, 69% males, mean aortic valve area 1.0 ± 0.4 cm²) and 37 age and sex-matched healthy volunteers underwent phenotypic characterization with comprehensive clinical, imaging, and biomarker evaluation. Asymmetric wall thickening on both echocardiography and cardiovascular magnetic resonance was defined as regional wall thickening ≥ 13 mm and > 1.5-fold the thickness of the opposing myocardial segment. Although no control subject had asymmetric wall thickening, it was observed in 26% (n = 43) of patients with aortic stenosis using magnetic resonance and 17% (n = 29) using echocardiography. Despite similar demographics, co-morbidities, valve narrowing, myocardial hypertrophy, and fibrosis, patients with asymmetric wall thickening had increased cardiac troponin I and brain natriuretic peptide concentrations (both P < 0.001). Over 28 [22, 33] months of follow-up, asymmetric wall thickening was an independent predictor of aortic valve replacement (AVR) or death whether detected by magnetic resonance [hazard ratio (HR) = 2.15; 95% confidence interval (CI) 1.29–3.59; P = 0.003] or echocardiography (HR = 1.79; 95% CI 1.08–3.69; P = 0.021). Asymmetric wall thickening is common in aortic stenosis and is associated with increased myocardial injury, left ventricular decompenzation, and adverse events. Its presence may help identify patients likely to proceed quickly towards AVR. https://clinicaltrials.gov/show/NCT01755936: NCT01755936.

Positron emission tomography (PET) with 18F-sodium fluoride (18F-NaF) has emerged as a promising non-invasive imaging modality to identify high-risk and ruptured atherosclerotic plaques. By visualizing microcalcification, 18F-NaF PET holds clinical promise in refining how we evaluate coronary artery disease, shifting our focus from assessing disease burden to atherosclerosis activity. In this review, we provide an overview of studies that have utilized 18F-NaF PET for imaging atherosclerosis. We discuss the associations between traditional coronary artery disease measures (risk factors) and 18F-NaF plaque activity. We also present the data on the histological validation as well as show how 18F-NaF uptake is associated with plaque morphology on intravascular and CT imaging. Finally, we discuss the technical challenges associated with 18F-NaF coronary PET highlighting recent advances in this area.