Advances in Diagnosis, Therapy, and Prognosis of Coronary Artery Disease Powered by Deep Learning Algorithms.

Percutaneous coronary intervention has been a standard treatment strategy for patients with coronary artery disease with continuous ebullient progress in technology and techniques. The application of artificial intelligence and deep learning in particular is currently boosting the development of interventional solutions, improving the efficiency and objectivity of diagnosis and treatment. The ever-growing amount of data and computing power together with cutting-edge algorithms pave the way for the integration of deep learning into clinical practice, which has revolutionized the interventional workflow in imaging processing, interpretation, and navigation. This review discusses the development of deep learning algorithms and their corresponding evaluation metrics together with their clinical applications. Advanced deep learning algorithms create new opportunities for precise diagnosis and tailored treatment with a high degree of automation, reduced radiation, and enhanced risk stratification. Generalization, interpretability, and regulatory issues are remaining challenges that need to be addressed through joint efforts from multidisciplinary community.

Implantation of bioresorbable scaffolds under guidance of optical coherence tomography: Feasibility and pilot clinical results of a systematic protocol.

BACKGROUND: Herein is hypothesised that a comprehensive optical coherence tomography (OCT)-guided implantation protocol for bioresorbable scaffolds (BRS) can improve expansion and apposition, thus resulting in better clinical outcomes, particularly in reducing thrombotic events. METHODS: Patients considered suitable for BRS therapy in de novo coronary lesions underwent OCT. The predominant type of plaque was classified as lipidic, fibrous or calcific. Accordingly they underwent tailored plaque preparation. After proper sizing, BRS was deployed and final OCT was acquired. Post-dilation was performed only in cases of suboptimal deployment. Procedural and 12 month clinical follow-up is reported. RESULTS: Twenty nine patients (41 lesions) who were considered clinically and angiographically suitable for BRS were enrolled, including challenging clinical scenarios such as ST-segment elevation myocardial infarction or CTOs. The OCT-guided protocol was feasible in 90.2% of the lesions: 14 (37.8%) lipidic, 11 (29.7%) fibrous, and 12 (32.4%) calcific. Three (8%) lesions classified as calcific were changed to treatment with metallic stent. BRS were implanted in 34 (91.9%) lesions, thereof 30 (88.2%) with optimal deployment in OCT. One (3.6%) periprocedural MI occurred, resulting in 3.6% target vessel failure and 0% scaffold thrombosis of any kind after a 12 month follow-up. CONCLUSIONS: OCT-guided BRS implantation is feasible in 90.2% of de novo lesions and results in optimal expansion and apposition, correlating with 3.6% incidence of target vessel failure and 0% scaffold thrombosis at 12 m follow-up, probably due to better selection of lesions amenable for BRS treatment and to a possibility of tailoring intervention to the type of plaque. These encouraging pilot results require confirmation in larger clinical studies.

Very late stent thrombosis in everolimus-eluting stent with predisposing mechanical factors: Differential features.

no abstract.

Macrophagic enhancement in optical coherence tomography imaging by means of superparamagnetic iron oxide nanoparticles.

BACKGROUND: The ability of optical coherence tomography (OCT) to visualise macrophages in vivo in coronary arteries is still controversial. We hypothesise that imaging of macrophages in OCT could be enhanced by means of superparamagnetic nanoparticles. METHODS: We compared the optical backscattering and attenuation of cell pellets containing RAW 264.7 macrophages with those of macrophagic cell pellets labelled with very small superparamagnetic oxydised nanoparticles (VSOP) by means of light intensity analysis in OCT. The labelled macrophages were incubated with VSOP at a concentration of 1 mM Fe, corresponding to intracellular iron concentrations of 8.8 pg/cell. To study the effect of intracellular accumulation on the backscattering, VSOP dilutions without cells were also compared. OCT pullbacks of the PCR tubes containing the cell pellets were obtained and light intensity analysis was performed on raw OCT images in polar view, after normalisation by the backscattering of the PCR tube. The backscattering was estimated by the peak normalised intensity, whilst the attenuation was estimated by the number of pixels between the peak and the normalised intensity 1 (peak-to-one). RESULTS: VSOP-loaded macrophages have higher backscattering than the corresponding unlabelled macrophages (peak normalised intensity 6.30 vs. 3.15) with also slightly higher attenuation (peak-toone 61 vs. 66 pixels). The backscattering of the nanoparticles in suspension was negligible in the light intensity analysis. CONCLUSIONS: VSOP increase significantly the optical backscattering of macrophages in the nearinfrared region, with minimal increase in signal attenuation. This finding enables the enhancement of macrophages in conventional OCT imaging with an easily implementable methodology.

Time course of vascular response after an a priori strategy of bare metal stent implantation post-dilated with a paclitaxel-coated balloon: Implementation of a three-dimensional analysis algorithm with optical coherence tomography.

BACKGROUND: An a priori combined therapy of a bare metal stent post-dilated with a paclitaxel- -coated balloon (PCB) was investigated with optical coherence tomography (OCT) at 2 and 6 months regarding vessel response. Previous studies have shown inconsistent results and the time course of vessel healing after such an interventional strategy is unknown. METHODS: Thirty-three de novo lesions in 32 patients were electively treated. Six-month OCT analysis was available in 24 lesions. Two-month OCT follow-up was obtained in 16 lesions. Sequential OCT at 2 and 6 months was available in 7 patients. A novel 3-dimensional picture of vessel segments as spread outs was implemented. RESULTS: Severe incomplete stent apposition (ISA) accompanied by significantly lower strut coverage were found at 2-month compared with 6-month follow-up (ISA struts: 11.4 ± 11.8% vs. 1.8 ± 4.8%, p = 0.001; uncovered struts: 14.5 ± 14.8% vs. 2.0 ± 5.3%, p = 0.001). ISA size diminished over time and the possibly observed phenomenon of positive vessel remodeling (remodeling volume: 4.9 ± 5.9 mm3 at 2-months vs. 2.0 ± 2.6 mm3 at 6-months; p = 0.042) was largely reversible in most lesions. CONCLUSIONS: Bare metal stenting with adjunctive application of paclitaxel by a coated bal-loon shows transient severe incomplete strut apposition, most likely due to focal positive ves-sel remodeling. Thus, caution is needed in bailout situations following a PCB angioplasty. A novel illustration of OCT parameters as "carpet views" enables a comprehensive analysis of investigated stents.

How should I treat impaired systolic function and clinical deterioration after surgery of type A aortic dissection?

BACKGROUND: A 50-year-old male with diagnosis of acute type A aortic dissection underwent surgical repair. Immediately after surgery the patient had transient ECG changes, a raise in serum cardiac markers and physical signs of heart failure. INVESTIGATION: Physical examination, electrocardiography, echocardiography (transthoracic and transoesophageal), coronary angiography, intravascular ultrasound. DIAGNOSIS: Type A aortic dissection. MANAGEMENT: Surgical repair, coronary angiography, percutaneous coronary intervention.

Five-year outcomes of percutaneous coronary intervention compared to bypass surgery in patients with multivessel disease involving the proximal left anterior descending artery: an ARTS-II sub-study.

AIMS: The aim of this study was to compare the 5-year outcomes of patients with multivessel disease (MVD) involving the proximal left anterior descending (LAD) artery who were treated with sirolimus drug-eluting stents (SES), bare metal stents (BMS) and coronary artery bypass surgery (CABG). METHODS AND RESULTS: Clinical outcomes were compared between the 682 patients enrolled in the ARTS-I and ARTS-II study who had MVD involving the proximal LAD, and were treated with BMS (27.4%), CABG (30.2%), and SES (42.4%). At 5-year follow-up the primary endpoint of major adverse cardiovascular and cerebrovascular events (MACCE) occurred in 33.7%, 18.0% and 24.9% of patients treated with BMS, CABG and SES, respectively (BMS vs. SES p=0.04, CABG vs. SES p=0.07). Unadjusted and adjusted rates of mortality and death/stroke/myocardial infarction (safety) were comparable between all three treatments. Repeat revascularisation was significantly lower following CABG irrespective of adjustment. The absolute difference in MACCE between patients with a logistic EuroSCORE above and below the mean (i.e., 2.09%) was 18.8% (p=0.001), and 1.9% (p=0.28) for CABG and SES, respectively. In patients with a high EuroSCORE, SES was a significantly safer treatment (p=0.04) whilst repeat revascularisation remained lower with CABG irrespective of the EuroSCORE. CONCLUSIONS: At 5-year follow-up CABG has comparable safety, and superior efficacy in terms of reducing repeat revascularisation compared to BMS and SES in the treatment of patients with MVD involving the proximal LAD however, appropriate patient selection remains imperative.

Impact of completeness of revascularization on the five-year outcome in percutaneous coronary intervention and coronary artery bypass graft patients (from the ARTS-II study).

The aim of this study was to compare clinical outcome at 5 years in patients with complete and incomplete revascularization treated with coronary artery bypass grafting (CABG) and percutaneous coronary intervention (PCI) with drug-eluting stents. Baseline and procedural angiograms and surgical case-record forms were centrally assessed for completeness of revascularization. Patients treated with PCI for incomplete revascularization were stratified according to Synergy between Percutaneous Coronary Intervention with Taxus and Cardiac Surgery (SYNTAX) score tertiles. Complete revascularization was achieved in 360 of 588 patients (61.2%) in the PCI with sirolimus-eluting stent group and 477 of 567 patients (84.1%) in the CABG group (p <0.05). There was no significant difference in 5-year survival without major adverse cardiac and cerebrovascular events (MACCEs; death, cerebrovascular accident, myocardial infarction, and any revascularization) between patients with complete and incomplete revascularization treated with PCI or CABG. Survival free from MACCEs in patients with incomplete revascularization treated with PCI was significantly lower than those with complete revascularization treated with CABG (hazard ratio 1.66, 0.96 to 1.80, log-rank p = 0.001). The 5-year MACCE-free survival in patients with incomplete revascularization treated with PCI stratified according to SYNTAX score tertiles showed a significantly lower MACCE survival in the higher SYNTAX tertile compared to the low (hazard ratio 0.56, 0.32 to 0.96, log-rank p = 0.04) and intermediate (hazard ratio 0.50, 0.28 to 0.91, log-rank p = 0.02) tertiles, whereas survival between the low and intermediate SYNTAX tertiles was not significantly different (hazard ratio 1.13, 0.60 to 2.13, log-rank p = 0.71). In conclusion, this study suggests that patients with complex coronary disease, in whom complete revascularization cannot be achieved with PCI, should be offered surgical revascularization. However, in those patients with less complex disease, PCI is a valid alternative even if complete revascularization cannot be achieved.

Real-time three-dimensional echocardiography in aortic stenosis: a novel, simple, and reliable method to improve accuracy in area calculation.

AIMS: The aim of the study was to validate a novel formula for aortic area, based on the principle of continuity equation (CE), that substitutes Doppler-derived stroke volume (SV) by SV directly measured with real-time three-dimensional (RT3D) echo and semi-automated border detection. RT3D has proved outstanding accuracy for left ventricular volume calculation. So far, however, neither this potential has been applied to haemodynamic assessment, nor RT3D has succeeded in the evaluation of aortic valve disease. METHODS AND RESULTS: Aortic area was measured in 41 patients with aortic stenosis using Gorlin's equation, Hakki's formula, Doppler CE, two-dimensional Simpson's volumetric method, and by the novel RT3D method. RT3D has the best linear association and absolute agreement with Gorlin of all non-invasive methods r = 0.902, intraclass correlation coefficient (ICC) = 0.846, better than CE (r = 0.646, ICC = 0.626) and two-dimensional volumetric method (r = 0.627, ICC = 0.378). Linear and Passing-Bablok regression show that RT3D fits better to Gorlin (r(2) = 0.814) than CE (r(2) = 0.417) and two-dimensional method (r(2) = 0.393). Its accuracy is comparable to Hakki's formula, routinely employed in catheter laboratories. Inter- and intraobserver agreements (ICC) were, respectively, 0.732 and 0.985, better than CE (0.662, 0.857). RT3D also grades most efficiently the severity of aortic stenosis as mild, moderate, or severe (weighted kappa = 0.932). RT3D underestimates aortic area (95% CI 0.084-0.193). ROC curves, however, show that the optimal cutoff point to consider aortic stenosis severity remains close to 1 cm(2) (1.06 cm(2)). CONCLUSIONS: RT3D is more accurate than CE and than two-dimensional volumetric methods to calculate area and to grade the severity of aortic stenosis. Area obtained by three-dimensional echo is slightly underestimated, but its range is clinically negligible.