Atherosclerotic plaque quantification from coronary CT angiography (CCTA) enables accurate assessment of coronary artery disease burden and prognosis. We sought to develop and validate a deep ...learning system for CCTA-derived measures of plaque volume and stenosis severity.
This international, multicentre study included nine cohorts of patients undergoing CCTA at 11 sites, who were assigned into training and test sets. Data were retrospectively collected on patients with a wide range of clinical presentations of coronary artery disease who underwent CCTA between Nov 18, 2010, and Jan 25, 2019. A novel deep learning convolutional neural network was trained to segment coronary plaque in 921 patients (5045 lesions). The deep learning network was then applied to an independent test set, which included an external validation cohort of 175 patients (1081 lesions) and 50 patients (84 lesions) assessed by intravascular ultrasound within 1 month of CCTA. We evaluated the prognostic value of deep learning-based plaque measurements for fatal or non-fatal myocardial infarction (our primary outcome) in 1611 patients from the prospective SCOT-HEART trial, assessed as dichotomous variables using multivariable Cox regression analysis, with adjustment for the ASSIGN clinical risk score.
In the overall test set, there was excellent or good agreement, respectively, between deep learning and expert reader measurements of total plaque volume (intraclass correlation coefficient ICC 0·964) and percent diameter stenosis (ICC 0·879; both p<0·0001). When compared with intravascular ultrasound, there was excellent agreement for deep learning total plaque volume (ICC 0·949) and minimal luminal area (ICC 0·904). The mean per-patient deep learning plaque analysis time was 5·65 s (SD 1·87) versus 25·66 min (6·79) taken by experts. Over a median follow-up of 4·7 years (IQR 4·0–5·7), myocardial infarction occurred in 41 (2·5%) of 1611 patients from the SCOT-HEART trial. A deep learning-based total plaque volume of 238·5 mm3 or higher was associated with an increased risk of myocardial infarction (hazard ratio HR 5·36, 95% CI 1·70–16·86; p=0·0042) after adjustment for the presence of deep learning-based obstructive stenosis (HR 2·49, 1·07–5·50; p=0·0089) and the ASSIGN clinical risk score (HR 1·01, 0·99–1·04; p=0·35).
Our novel, externally validated deep learning system provides rapid measurements of plaque volume and stenosis severity from CCTA that agree closely with expert readers and intravascular ultrasound, and could have prognostic value for future myocardial infarction.
National Heart, Lung, and Blood Institute and the Miriam & Sheldon G Adelson Medical Research Foundation.
Pericoronary adipose tissue (PCAT) attenuation and low-attenuation noncalcified plaque (LAP) burden can both predict outcomes.
This study sought to assess the relative and additive values of PCAT ...attenuation and LAP to predict future risk of myocardial infarction.
In a post hoc analysis of the multicenter SCOT-HEART (Scottish Computed Tomography of the Heart) trial, the authors investigated the relationships between the future risk of fatal or nonfatal myocardial infarction and PCAT attenuation measured from coronary computed tomography angiography (CTA) using multivariable Cox regression models including plaque burden, obstructive coronary disease, and cardiac risk score (incorporating age, sex, diabetes, smoking, hypertension, hyperlipidemia, and family history).
In 1,697 evaluable participants (age: 58 ± 10 years), there were 37 myocardial infarctions after a median follow-up of 4.7 years. Mean PCAT was −76 ± 8 HU and median LAP burden was 4.20% (IQR: 0%-6.86%). PCAT attenuation of the right coronary artery (RCA) was predictive of myocardial infarction (HR: 1.55; P = 0.017, per 1 SD increment) with an optimum threshold of −70.5 HU (HR: 2.45; P = 0.01). In multivariable analysis, adding PCAT-RCA of ≥−70.5 HU to an LAP burden of >4% (the optimum threshold for future myocardial infarction; HR: 4.87; P < 0.0001) led to improved prediction of future myocardial infarction (HR: 11.7; P < 0.0001). LAP burden showed higher area under the curve compared to PCAT attenuation for the prediction of myocardial infarction (AUC = 0.71 95% CI: 0.62-0.80 vs AUC = 0.64 95% CI: 0.54-0.74; P < 0.001), with increased area under the curve when the 2 metrics are combined (AUC = 0.75 95% CI: 0.65-0.85; P = 0.037).
Coronary CTA–defined LAP burden and PCAT attenuation have marked and complementary predictive value for the risk of fatal or nonfatal myocardial infarction.
Display omitted
Coronary 18F-sodium-fluoride (18F-NaF) positron emission tomography (PET) showed promise in imaging coronary artery disease activity. Currently image processing remains subjective due to the need for ...manual registration of PET and computed tomography (CT) angiography data. We aimed to develop a novel fully automated method to register coronary 18F-NaF PET to CT angiography using pseudo-CT generated by generative adversarial networks (GAN).
A total of 169 patients, 139 in the training and 30 in the testing sets were considered for generation of pseudo-CT from non-attenuation corrected (NAC) PET using GAN. Non-rigid registration was used to register pseudo-CT to CT angiography and the resulting transformation was used to align PET with CT angiography. We compared translations, maximal standard uptake value (SUVmax) and target to background ratio (TBRmax) at the location of plaques, obtained after observer and automated alignment.
Automatic end-to-end registration was performed for 30 patients with 88 coronary vessels and took 27.5 seconds per patient. Difference in displacement motion vectors between GAN-based and observer-based registration in the x-, y-, and z-directions was 0.8 ± 3.0, 0.7 ± 3.0, and 1.7 ± 3.9 mm, respectively. TBRmax had a coefficient of repeatability (CR) of 0.31, mean bias of 0.03 and narrow limits of agreement (LOA) (95% LOA: − 0.29 to 0.33). SUVmax had CR of 0.26, mean bias of 0 and narrow LOA (95% LOA: − 0.26 to 0.26).
Pseudo-CT generated by GAN are perfectly registered to PET can be used to facilitate quick and fully automated registration of PET and CT angiography.
We aimed to establish the observer repeatability and interscan reproducibility of coronary 18F-sodium-fluoride positron emission tomography (PET) uptake using a novel semi-automated approach, ...coronary microcalcification activity (CMA).
Patients with multivessel coronary artery disease underwent repeated hybrid PET and computed tomography angiography (CTA) imaging (PET/CTA). CMA was defined as the integrated standardized uptake values (SUV) in the entire coronary tree exceeding 2 standard deviations above the background SUV. Coefficients of repeatability between the same observer (intraobserver repeatability), between 2 observers (interobserver repeatability) and coefficient of reproducibility between 2 scans (interscan reproducibility), were determined at vessel and patient level.
In 19 patients, CMA was assessed twice in 43 coronary vessels on two PET/CT scans performed 12 ± 5 days apart. There was excellent intraclass correlation for intraobserver and interobserver repeatability as well as interscan reproducibility (all ≥ 0.991). There was 100% intraobserver, interobserver and interscan agreement for the presence (CMA > 0) or absence (CMA = 0) of coronary18F-NaF uptake. Mean CMA was 3.12 ± 0.62 with coefficients of repeatability of ≤ 10% for all measures: intraobserver 0.24 and 0.22, interobserver 0.30 and 0.29 and interscan 0.33 and 0.32 at a per-vessel and per-patient level, respectively.
CMA is a repeatable and reproducible global measure of coronary atherosclerotic activity.
Standard methods for quantifying positron emission tomography (PET) uptake in the aorta are time consuming and may not reflect overall vessel activity. We describe aortic microcalcification activity ...(AMA), a novel method for quantifying 18F-sodium fluoride (18F-NaF) uptake in the thoracic aorta.
Twenty patients underwent two hybrid 18F-NaF PET and computed tomography (CT) scans of the thoracic aorta less than three weeks apart. AMA, as well as maximum (TBRmax) and mean (TBRmean) tissue to background ratios, were calculated by two trained operators. Intra-observer repeatability, inter-observer repeatability and scan-rescan reproducibility were assessed. Each 18F-NaF quantification method was compared to validated cardiovascular risk scores.
Aortic microcalcification activity demonstrated excellent intra-observer (intraclass correlation coefficient 0.98) and inter-observer (intraclass correlation coefficient 0.97) repeatability with very good scan-rescan reproducibility (intraclass correlation coefficient 0.86) which were similar to previously described TBRmean and TBRmax methods. AMA analysis was much quicker to perform than standard TBR assessment (3.4min versus 15.1min, P<0.0001). AMA was correlated with Framingham stroke risk scores and Framingham risk score for hard cononary heart disease.
AMA is a simple, rapid and reproducible method of quantifying global 18F-NaF uptake across the ascending aorta and aortic arch that correlates with cardiovascular risk scores.
To evaluate the impact of respiratory-averaged computed tomography attenuation correction (RACTAC) compared to standard single-phase computed tomography attenuation correction (CTAC) map, on the ...quantitative measures of coronary atherosclerotic lesions of 18F-sodium fluoride (18F-NaF) uptake in hybrid positron emission tomography and computed tomography (PET/CT).
This study comprised 23 patients who underwent 18F-NaF coronary PET in a hybrid PET/CT system. All patients had a standard single-phase CTAC obtained during free-breathing and a 4D cine-CT scan. From the cine-CT acquisition, RACTAC maps were obtained by averaging all images acquired over 5 seconds. PET reconstructions using either CTAC or RACTAC were compared. The quantitative impact of employing RACTAC was assessed using maximum target-to-background (TBRMAX) and coronary microcalcification activity (CMA). Statistical differences were analyzed using reproducibility coefficients and Bland-Altman plots.
In 23 patients, we evaluated 34 coronary lesions using CTAC and RACTAC reconstructions. There was good agreement between CTAC and RACTAC for TBRMAX (median Interquartile range): CTAC = 1.65 1.23 to 2.38, RACTAC = 1.63 1.23 to 2.33, p = 0.55), with coefficient of reproducibility of 0.18, and CMA: CTAC = 0.10 0 to 1.0, RACTAC = 0.15 0 to 1.03, p = 0.55 with coefficient of reproducibility of 0.17
Respiratory-averaged and standard single-phase attenuation correction maps provide similar and reproducible methods of quantifying coronary 18F-NaF uptake on PET/CT.
Positron emission tomography (PET) is the clinical gold standard for quantifying myocardial blood flow (MBF). Pericoronary adipose tissue (PCAT) attenuation may detect vascular inflammation ...indirectly. We examined the relationship between MBF by PET and plaque burden and PCAT on coronary CT angiography (CCTA).
This post hoc analysis of the PACIFIC trial included 208 patients with suspected coronary artery disease (CAD) who underwent 15OH2O PET and CCTA. Low-attenuation plaque (LAP, < 30HU), non-calcified plaque (NCP), and PCAT attenuation were measured by CCTA.
In 582 vessels, 211 (36.3%) had impaired per-vessel hyperemic MBF (≤ 2.30 mL/min/g). In multivariable analysis, LAP burden was independently and consistently associated with impaired hyperemic MBF (P = 0.016); over NCP burden (P = 0.997). Addition of LAP burden improved predictive performance for impaired hyperemic MBF from a model with CAD severity and calcified plaque burden (P < 0.001). There was no correlation between PCAT attenuation and hyperemic MBF (r = − 0.11), and PCAT attenuation was not associated with impaired hyperemic MBF in univariable or multivariable analysis of all vessels (P > 0.1).
In patients with stable CAD, LAP burden was independently associated with impaired hyperemic MBF and a stronger predictor of impaired hyperemic MBF than NCP burden. There was no association between PCAT attenuation and hyperemic MBF.
Background
Current
18
F-NaF assessments of aortic valve microcalcification using
18
F-NaF PET/CT are based on evaluations of end-diastolic or cardiac motion-corrected (ECG-MC) images, which are ...affected by both patient and respiratory motion. We aimed to test the impact of employing a triple motion correction technique (3 × MC), including cardiorespiratory and gross patient motion, on quantitative and qualitative measurements.
Materials and methods
Fourteen patients with aortic stenosis underwent two repeat 30-min PET aortic valve scans within (29 ± 24) days. We considered three different image reconstruction protocols; an end-diastolic reconstruction protocol (standard) utilizing 25% of the acquired data, an ECG-gated (four ECG gates) reconstruction (ECG-MC), and a triple motion-corrected (3 × MC) dataset which corrects for both cardiorespiratory and patient motion. All datasets were compared to aortic valve calcification scores (AVCS), using the Agatston method, obtained from CT scans using correlation plots. We report SUV
max
values measured in the aortic valve and maximum target-to-background ratios (TBR
max
) values after correcting for blood pool activity.
Results
Compared to standard and ECG-MC reconstructions, increases in both SUV
max
and TBR
max
were observed following 3 × MC (SUV
max
: Standard = 2.8 ± 0.7, ECG-MC = 2.6 ± 0.6, and 3 × MC = 3.3 ± 0.9; TBR
max
: Standard = 2.7 ± 0.7, ECG-MC = 2.5 ± 0.6, and 3 × MC = 3.3 ± 1.2, all
p
values ≤ 0.05). 3 × MC had improved correlations (R
2
value) to the AVCS when compared to the standard methods (SUV
max
: Standard = 0.10, ECG-MC = 0.10, and 3 × MC = 0.20; TBR
max
: Standard = 0.20, ECG-MC = 0.28, and 3 × MC = 0.46).
Conclusion
3 × MC improves the correlation between the AVCS and SUV
max
and TBR
max
and should be considered in PET studies of aortic valves using
18
F-NaF.
We tested the repeatability of myocardial blood flow (MBF) quantified using 82Rb with and without motion correction (MC) and with arterial input functions estimated from left ventricle (LV) and ...atrium (LA).
Twenty-one patients referred for clinical 82Rb PET/CT underwent repeated rest scans in a single imaging session. Global MBF was quantified using three different assessments by two operators: (1) automatic processing without MC and LV arterial input function (AIF), (2) with MC and LV-AIF, and (3) with MC and LA-AIF. Inter-scan and inter-operator repeatability were tested using coefficient of variation (CV).
MC with LV-AIF did not change MBF (no MC: 1.01 ± 0.30 mL/min/g vs MC with LV-AIF: 1.01 ± 0.29, P = 0.70), whereas MC with LA-AIF showed significantly lower MBF assessments (0.95 ± 0.28 mL/min/g, P = 0.0006). We report significant improvement for test-retest reproducibility for global MBF following MC (CV; No MC: 16.0, MC (LV-AIF): 9.2, MC (LA-AIF): 8.8). Good inter-operator repeatability was observed for LV-AIF (CV = 4.7) and LA-AIF (CV = 5.6) for global MBF assessments.
MC significantly improved the test-retest repeatability between operators and between scans. MBF obtained after MC with LV-AIF were comparable, whereas MBFs after MC and LA-AIF were significantly reduced.
Diabetes mellitus (DM) is increasingly prevalent among contemporary populations referred for cardiac stress testing, but its potency as a predictor for major adverse cardiovascular events (MACE) vs ...other clinical variables is not well delineated.
From 19,658 patients who underwent SPECT-MPI, we identified 3122 patients with DM without known coronary artery disease (CAD) (DM+/CAD−) and 3564 without DM with known CAD (DM−/CAD+). Propensity score matching was used to control for the differences in characteristics between DM+/CAD− and DM−/CAD+ groups. There was comparable MACE in the matched DM+/CAD− and DM−/CAD+ groups (HR 1.15, 95% CI 0.97-1.37). By Chi-square analysis, type of stress (exercise or pharmacologic), total perfusion deficit (TPD), and left ventricular function were the most potent predictors of MACE, followed by CAD and DM status. The combined consideration of mode of stress, TPD, and DM provided synergistic stratification, an 8.87-fold (HR 8.87, 95% CI 7.27-10.82) increase in MACE among pharmacologically stressed patients with DM and TPD > 10% (vs non-ischemic, exercised stressed patients without DM).
Propensity-matched patients with DM and no known CAD have similar MACE risk compared to patients with known CAD and no DM. DM is synergistic with mode of stress testing and TPD in predicting the risk of cardiac stress test patients.