X-ray coronary angiography is a primary imaging technique for diagnosing coronary diseases. Although quantitative coronary angiography (QCA) provides morphological information of coronary arteries ...with objective quantitative measures, considerable training is required to identify the target vessels and understand the tree structure of coronary arteries. Despite the use of computer-aided tools, such as the edge-detection method, manual correction is necessary for accurate segmentation of coronary vessels. In the present study, we proposed a robust method for major vessel segmentation using deep learning models with fully convolutional networks. When angiographic images of 3302 diseased major vessels from 2042 patients were tested, deep learning networks accurately identified and segmented the major vessels in X-ray coronary angiography. The average F1 score reached 0.917, and 93.7% of the images exhibited a high F1 score > 0.8. The most narrowed region at the stenosis was distinctly captured with high connectivity. Robust predictability was validated for the external dataset with different image characteristics. For major vessel segmentation, our approach demonstrated that prediction could be completed in real time with minimal image preprocessing. By applying deep learning segmentation, QCA analysis could be further automated, thereby facilitating the use of QCA-based diagnostic methods.
Invasive fractional flow reserve (FFR) is a standard tool for identifying ischemia-producing coronary stenosis. However, in clinical practice, over 70% of treatment decisions still rely on visual ...estimation of angiographic stenosis, which has limited accuracy (about 60%-65%) for the prediction of FFR < 0.80. One of the reasons for the visual-functional mismatch is that myocardial ischemia can be affected by the supplied myocardial size, which is not always evident by coronary angiography. The aims of this study were to develop an angiography-based machine learning (ML) algorithm for predicting the supplied myocardial volume for a stenosis, as measured using coronary computed tomography angiography (CCTA), and then to build an angiography-based classifier for the lesions with an FFR < 0.80 versus ≥ 0.80.
A retrospective study was conducted using data from 1,132 stable and unstable angina patients with 1,132 intermediate lesions who underwent invasive coronary angiography, FFR, and CCTA at the Asan Medical Center, Seoul, Korea, between 1 May 2012 and 30 November 2015. The mean age was 63 ± 10 years, 76% were men, and 72% of the patients presented with stable angina. Of these, 932 patients (assessed before 31 January 2015) constituted the training set for the algorithm, and 200 patients (assessed after 1 February 2015) served as a test cohort to validate its diagnostic performance. Additionally, external validation with 79 patients from two centers (CHA University, Seongnam, Korea, and Ajou University, Suwon, Korea) was conducted. After automatic contour calibration using the caliber of guiding catheter, quantitative coronary angiography was performed using the edge-detection algorithms (CAAS-5, Pie-Medical). Clinical information was provided by the Asan BiomedicaL Research Environment (ABLE) system. The CCTA-based myocardial segmentation (CAMS)-derived myocardial volume supplied by each vessel (right coronary artery RCA, left anterior descending LAD, left circumflex LCX) and the myocardial volume subtended to a stenotic segment (CAMS-%Vsub) were measured for labeling. The ML for (1) predicting vessel territories (CAMS-%LAD, CAMS-%LCX, and CAMS-%RCA) and CAMS-%Vsub and (2) identifying the lesions with an FFR < 0.80 was constructed. Angiography-based ML, employing a light gradient boosting machine (GBM), showed mean absolute errors (MAEs) of 5.42%, 8.57%, and 4.54% for predicting CAMS-%LAD, CAMS-%LCX, and CAMS-%RCA, respectively. The percent myocardial volumes predicted by ML were used to predict the CAMS-%Vsub. With 5-fold cross validation, the MAEs between ML-predicted percent myocardial volume subtended to a stenotic segment (ML-%Vsub) and CAMS-%Vsub were minimized by the elastic net (6.26% ± 0.55% for LAD, 5.79% ± 0.68% for LCX, and 2.95% ± 0.14% for RCA lesions). Using all attributes (age, sex, involved vessel segment, and angiographic features affecting the myocardial territory and stenosis degree), the ML classifiers (L2 penalized logistic regression, support vector machine, and random forest) predicted an FFR < 0.80 with an accuracy of approximately 80% (area under the curve AUC = 0.84-0.87, 95% confidence intervals 0.71-0.94) in the test set, which was greater than that of diameter stenosis (DS) > 53% (66%, AUC = 0.71, 95% confidence intervals 0.65-0.78). The external validation showed 84% accuracy (AUC = 0.89, 95% confidence intervals 0.83-0.95). The retrospective design, single ethnicity, and the lack of clinical outcomes may limit this prediction model's generalized application.
We found that angiography-based ML is useful to predict subtended myocardial territories and ischemia-producing lesions by mitigating the visual-functional mismatch between angiographic and FFR. Assessment of clinical utility requires further validation in a large, prospective cohort study.
Comparative outcomes of coronary artery bypass grafting (CABG) and percutaneous coronary intervention (PCI) for left main coronary artery (LMCA) disease were previously reported. However, data on ...very long-term (>10 years) outcomes are limited.
The authors compare 10-year outcomes after PCI and CABG for LMCA disease.
In this observational study of the MAIN-COMPARE (Revascularization for Unprotected Left Main Coronary Artery Stenosis: Comparison of Percutaneous Coronary Angioplasty versus Surgical Revascularization) registry, the authors evaluated 2,240 patients with unprotected LMCA disease who underwent PCI (n = 1,102) or underwent CABG (n = 1,138) between January 2000 and June 2006. Adverse outcomes (death; a composite outcome of death, Q-wave myocardial infarction, or stroke; and target-vessel revascularization) were compared with the use of propensity scores and inverse-probability-weighting adjustment. The follow-up was extended to at least 10 years of all patients (median 12.0 years).
In the overall cohort, there was no significant difference in adjusted risks of death and the composite outcome between the groups up to 10 years. The risk of target-vessel revascularization was significantly higher in the PCI group. In the cohort comparing drug-eluting stents and concurrent CABG, the 2 study groups did not differ significantly in the risks of death and the composite outcome at 5 years. However, after 5 years, drug-eluting stents were associated with higher risks of death (hazard ratio: 1.35; 95% confidence interval: 1.00 to 1.81) and the composite outcome (hazard ratio: 1.46; 95% confidence interval: 1.10 to 1.94) compared with CABG.
In patients with significant LMCA disease, as compared with CABG, PCI showed similar rates of death and serious composite outcomes, but a higher rate of target-vessel revascularization at 10 years. However, CABG showed lower mortality and serious composite outcome rates compared with PCI with drug-eluting stents after 5 years. (Revascularization for Unprotected Left Main Coronary Artery Stenosis: Comparison of Percutaneous Coronary Angioplasty versus Surgical Revascularization MAIN-COMPARE; NCT02791412)
Display omitted
Post-transcatheter aortic valve implantation (TAVI) computed tomography (CT) findings have not been fully elucidated, except hypoattenuating leaflet thickening (HALT). The objective of this study was ...to describe cardiac CT findings after TAVI, and investigate factors associated with HALT. This retrospective study included patients who underwent TAVI and post-TAVI cardiac CT scans. On CT, abnormal findings such as hypoattenuating subvalvular thickening (HAST), thrombus within the sinus of Valsalva, HALT, and leaflet motion limitation were thoroughly reviewed. Clinical and CT findings were compared between patients with HALT and those without HALT. Logistic regression analysis was performed to determine factors associated with HALT. A total of 138 patients (64 male, mean 78.5 ± 5.2 years of age) with post-TAVI CT scans were included. The median duration from TAVI to CT was 17.5 days (interquartile range, 3 to 390.8 days). HAST and thrombus within the sinus of Valsalva were detected in 32 (23%) and 5 (4%) patients, respectively. HALT and leaflet motion limitations were found in 25 (18%) and 20 (14%) of patients, respectively. Pannus was diagnosed in 2 patients. TAVI device implant duration (odds ratio OR, 1.5; p = 0.01), hypertension (OR, 0.2; p = 0.03), and HAST (OR, 4.9; p = 0.003) were associated with HALT. Implant durations were longer in patients with HAST, HALT, or leaflet motion limitation (p < 0.05, for all). In conclusion, HAST, HALT, thrombus within the sinus of Valsalva, and leaflet motion limitation are not uncommon after TAVI. Implant duration, hypertension, and HAST are associated with HALT.
Owing to the differential propensity for bleeding and ischemic events with response to antiplatelet therapy, the safety and effectiveness of potent P2Y12 inhibitor ticagrelor in East Asian ...populations remain uncertain.
In this multicenter trial, 800 Korean patients hospitalized for acute coronary syndromes with or without ST elevation and intended for invasive management were randomly assigned to receive, in a 1:1 ratio, ticagrelor (180 mg loading dose, 90 mg twice daily thereafter) or clopidogrel (600 mg loading dose, 75 mg daily thereafter). The primary safety outcome was clinically significant bleeding (a composite of major bleeding or minor bleeding according to PLATO (Platelet Inhibition and Patient Outcomes) criteria at 12 months.
At 12 months, the incidence of clinically significant bleeding was significantly higher in the ticagrelor group than in the clopidogrel group (11.7% 45/400 vs 5.3% 21/400; hazard ratio HR, 2.26; 95% confidence interval CI, 1.34 to 3.79;
=0.002). The incidences of major bleeding (7.5% 29/400 vs 4.1% 16/400,
=0.04) and fatal bleeding (1% 4/400 vs 0%,
=0.04) were also higher in the ticagrelor group. The incidence of death from cardiovascular causes, myocardial infarction, or stroke was not significantly different between the ticagrelor group and the clopidogrel group (9.2% 36/400 vs 5.8% 23/400; HR, 1.62; 95% CI, 0.96 to 2.74;
=0.07). Overall safety and effectiveness findings were similar with the use of several different analytic methods and in multiple subgroups.
In Korean acute coronary syndrome patients intended to receive early invasive management, standard-dose ticagrelor as compared with clopidogrel was associated with a higher incidence of clinically significant bleeding. The numerically higher incidence of ischemic events should be interpreted with caution, given the present trial was underpowered to draw any conclusion regarding efficacy.
URL: https://www.clinicaltrials.gov. Unique identifier: NCT02094963.
There is limited data regarding the association between sarcopenia and clinical outcomes in patients who underwent transcatheter aortic valve implantation (TAVI). From the prospective ASAN-TAVI ...registry, we evaluated a total of 522 patients with severe aortic stenosis who underwent TAVI between March 2010 and November 2018. Routine pre-TAVI computed tomography scan was used to calculate the skeletal muscle index (SMI), which was defined as skeletal muscle area at the L3 level divided by height squared; subject patients were classified into the gender-specific tertile groups of SMI. The patients’ mean age was 79 years and 49% were men. Mean SMI values were 41.3 ± 6.7 cm2/m2 in men and 34.1 ± 6.5 cm2/m2 in women. The Kaplan–Meier estimates of all-cause mortality at 12 months were higher in the low-tertile group than in the mid- and high-tertile groups (15.5%, 7.1%, and 6.2%, respectively; p = 0.036). In multivariate analysis, low-tertile of SMI was an independent predictor of mortality (vs high-tertile of SMI, hazard ratio 2.69; 95% confidence interval, 1.18 to 6.12; p = 0.019). The all-cause mortality was substantially higher in the groups with high-surgical risk plus low SMI tertile. The risk assessment with addition of SMI on conventional STS-PROM score was significantly improved by statistical measures of model reclassification and discrimination. In patients who underwent TAVI, sarcopenia measured by SMI was significantly associated with an increased risk of 1-year mortality. The prognostic impact of SMI-measured sarcopenia was more prominent in patients with high surgical risks.
•Evidence for optimal antithrombotic regimen for AF with stable CAD is limited.•This meta-analysis compared outcomes between OAC monotherapy and OAC plus SAPT.•OAC monotherapy showed similar efficacy ...but significantly lower risk of bleeding.•Further evidence regarding DOAC in AF patients with stable CAD is required.
Guidelines recommend oral anticoagulant (OAC) monotherapy without antiplatelet therapy (APT) in patients with nonvalvular atrial fibrillation (AF) with stable coronary artery disease (CAD) of >1 year after myocardial infarction or percutaneous coronary intervention. More evidences are required for the safety and efficacy of OAC monotherapy compared with OAC plus APT. PubMed, EMBASE, and Cochrane Database of Systematic Reviews were systematically searched up to February 2019. Nonrandomized studies and randomized clinical trials comparing OAC monotherapy with OAC plus single APT (SAPT) for patients with stable CAD and nonvalvular AF. The primary end point was major adverse cardiovascular events (composite of ischemic or thrombotic events) and secondary outcomes included major bleeding, stroke, all-cause death, and net adverse events (composite of ischemic, thrombotic, or bleeding events). From 6 trials, 8,855 patients were included. There was no significant difference in major adverse cardiovascular event in patients with AF treated using OAC plus SAPT compared with those treated with OAC monotherapy (hazard ratio HR 1.09; 95% confidence interval CI 0.92 to 1.29). OAC plus SAPT was associated with a significantly higher risk of major bleeding compared with OAC monotherapy (HR 1.61; 95% CI 1.38 to 1.87), as well as in terms of net adverse event (HR 1.21; 95% CI 1.02 to 1.43). There were no significant differences in rates of stroke and all-cause death. In conclusion, in this meta-analysis, OAC monotherapy and OAC plus SAPT treatment showed similar effectiveness, but OAC monotherapy was significantly associated with a lower risk of bleeding compared with OAC plus SAPT in patients with nonvalvular AF and stable CAD.
Myocardial viability test to guide revascularization remains uncertain in patients with ischemic cardiomyopathy. We evaluated the different impacts of revascularization on cardiac mortality according ...to the extent of myocardial scar assessed by cardiac magnetic resonance (CMR) with late gadolinium enhancement (LGE) in patients with ischemic cardiomyopathy. A total of 404 consecutive patients with significant coronary artery disease and an ejection fraction ≤35% were assessed by LGE-CMR before revascularization. Of them, 306 patients underwent revascularization and 98 patients received medical treatment alone. The primary outcome was cardiac death. During a median follow-up of 6.3 years, cardiac death occurred in 158 patients (39.1%). Revascularization was associated with a significantly lower risk of cardiac death than medical treatment alone in the overall population (adjusted hazard ratio aHR 0.29, 95% confidence interval (CI) 0.19 to 0.45, p <0.001). There was a significant interaction between the number of segments with >75% transmural LGE and revascularization on the risk of cardiac death (p = 0.037 for interaction). In patients with limited myocardial scar (<6 segments with >75% transmural LGE, n = 354), revascularization had a significantly lower risk of cardiac death than medical treatment alone (aHR 0.24, 95% CI 0.15 to 0.37, p <0.001); in patients with extensive myocardial scar (≥6 segments with >75% transmural LGE, n = 50), there was no significant difference between revascularization and medical treatment alone regarding the risk of cardiac death (aHR 1.33, 95% CI 0.46 to 3.80, p = 0.60). In conclusion, the assessment of myocardial scar by LGE-CMR may be helpful in the decision-making process for revascularization in patients with ischemic cardiomyopathy.
To compare 10‐year outcomes after implantation of sirolimus‐eluting stents (SES) versus paclitaxel‐eluting stents (PES) for left main coronary artery (LMCA) stenosis. Very long‐term outcome data of ...patients with LMCA disease treated with drug‐eluting stents (DES) have not been well described. In 10‐year extended follow‐up of the MAINCOMPARE registry, we evaluated 778 patients with unprotected LMCA stenosis who were treated with SES (n = 607) or PES (n = 171) between January 2000 and June 2006. The primary composite outcome (a composite of death, myocardial infarction MI or target‐vessel revascularization TVR) was compared with an inverse‐probability‐of‐treatment‐weighting (IPTW) adjustment. Clinical events have linearly accumulated over 10 years. At 10 years, there were no significant differences between SES and PES in the observed rates of the primary composite outcome (42.0% vs. 47.4%; hazard ratio HR 0.85; 95% confidence interval CI 0.66–1.10), and definite stent thrombosis (ST) (1.9% vs. 1.8%; HR 1.02, 95% CI 0.28–3.64). In the IPTW‐adjusted analyses, there were no significant differences between SES and PES in the risks for the primary composite outcome (HR 0.89, 95% CI 0.65–1.14) or definite ST (adjusted HR 1.05, 95% CI 0.29–3.90). In patients who underwent DES implantation, high overall adverse clinical event rates (with a linearly increasing event rate over time) were observed during extended follow‐up. At 10 years, there were no measurable differences in outcomes between patients treated with SES vs. PES for LMCA disease. The incidence of stent thrombosis was quite low and comparable between the groups.