Definições das Recomendações e Evidências […] Diretrizes da Sociedade Brasileira de Cardiologia sobre Angina Instável e Infarto Agudo do Miocárdio sem Supradesnível do Segmento ST – 2021 Definições das Recomendações e Evidências […] Diretrizes da Sociedade Brasileira de Cardiologia sobre Angina Instável e Infarto Agudo do Miocárdio sem Supradesnível do Segmento ST – 2021

We developed a fully automated, two-step deep learning approach for characterizing coronary calcified plaque in intravascular optical coherence tomography (IVOCT) images. First, major calcification lesions were detected from an entire pullback using a 3D convolutional neural network (CNN). Second, a SegNet deep learning model with the Tversky loss function was used to segment calcified plaques in the major calcification lesions. The fully connected conditional random field and the frame interpolation of the missing calcification frames were used to reduce classification errors. We trained/tested the networks on a large dataset comprising 8,231 clinical images from 68 patients with 68 vessels and 4,320 ex vivo cadaveric images from 4 hearts with 4 vessels. The 3D CNN model detected major calcifications with high sensitivity (97.7%), specificity (87.7%), and F1 score (0.922). Compared to the standard one-step approach, our two-step deep learning approach significantly improved sensitivity (from 77.5% to 86.2%), precision (from 73.5% to 75.8%), and F1 score (from 0.749 to 0.781). We investigated segmentation performance for varying numbers of training samples; at least 3,900 images were required to obtain stable segmentation results. We also found very small differences in calcification attributes (e.g., angle, thickness, and depth) and identical calcium scores on repetitive pullbacks, indicating excellent reproducibility. Applied to new clinical pullbacks, our method has implications for real-time treatment planning and imaging research.

BACKGROUND: Use of intracoronary imaging is associated with improved outcomes in patients undergoing percutaneous coronary intervention (PCI). Yet, the impact of intracoronary imaging on real-time physician decision-making during PCI is not fully known. METHODS: The LightLab Initiative is a multicenter, prospective, observational study designed to characterize the use of a standardized optical coherence tomography (OCT) workflow during PCI. Participating physicians performed pre-PCI and post-PCI OCT in accordance with this workflow and operator assessments of lesion characteristics and treatment plan were recorded for each lesion based on angiography alone and following OCT. Physicians were categorized as having low (n=15), intermediate (n=13), or high (n=14) OCT use in the year preceding participation. RESULTS: Among 925 patients with 1328 lesions undergoing PCI, the prescribed OCT workflow was followed in 773 (84%) of patients with 836 lesions. Operator lesion assessment and decision-making during PCI changed with OCT use in 86% (721/836) of lesions. Pre-PCI OCT use changed operator decision-making in 80% of lesions, including lesion assessment (45%), vessel preparation strategy (27%), stent diameter (37%), and stent length (36%). Post-PCI OCT changed stent optimization decision-making in 31% of lesions. These findings were consistent across strata of physician prior OCT experience. CONCLUSIONS: A standardized OCT workflow impacted PCI decision-making in 86% of lesions, with a predominant effect on pre-PCI lesion assessment and planning of treatment strategy. This finding was consistent regardless of operator experience level and provides insight into mechanisms by which intravascular imaging might improve PCI outcomes.

Despite ongoing progress in stent technology and deployment techniques, in-stent restenosis (ISR) still remains a major issue following percutaneous coronary intervention (PCI) and accounts for 10.6% of all interventions in the United States. With the continuous rise in ISR risk factors such as obesity and diabetes, along with an increase in the treatment of complex lesions with high-risk percutaneous coronary intervention (CHIP), a substantial growth in ISR burden is expected. This review aims to provide insight into the mechanisms, classification, and management of ISR, with a focus on exploring innovative approaches to tackle this complication comprehensively, along with a special section addressing the approach to complex calcified lesions.

Endovascular Therapeutic hypothermia (ETH) reduces the damage caused by postischemia reperfusion injury syndrome in cardiopulmonary arrest and has already established its role in patients with sudden death; however, its role in ST-segment elevation myocardial infarction (STEMI) remains controversial. The objectives of this study were to investigate the safety, feasibility, and 30-day efficacy of rapid induction of therapeutic hypothermia as adjunctive therapy to percutaneous coronary intervention (PCI) in patients with anterior and inferior STEMIs. This was a prospective, controlled, randomized, two-arm, prospective, interventional study of patients admitted to the emergency department within 6 hours of angina onset, with anterior or inferior STEMI eligible for PCI. Subjects were randomized to the hypothermia group (primary PCI+ETH) or to the control group (primary PCI) at a 4:1 ratio. The ETH was induced by 1 L cold saline (1–4°C) associated with the Proteus™ System, by cooling for at least 18 minutes before coronary reperfusion with a target temperature of 32°C ± 1°C. Maintenance of ETH was conducted for 1–3 hours, and active reheating was done at a rate of 1°C/h for 4 hours. Primary safety outcomes were the feasibility of ETH in the absence of (1) door-to-balloon (DTB) delay; (2) major adverse cardiac events (MACE) within 30 days after randomization. The primary outcomes of effectiveness were infarct size (IS) and left ventricular ejection fraction (LVEF) at 30 days. An as-treated statistical analysis was performed. Fifty patients were included: 35 (70%) randomized to the hypothermia group and 15 (30%) to the control group. The mean age was 58 ± 12 years; 78% were men; and associated diseases were 60% hypertension, 42% diabetes, and 72% dyslipidemia. The compromised myocardial wall was anterior in 38% and inferior in 62%, and the culprit vessels were left anterior descending artery (LAD) (40%), right coronary artery (38%), and left circumflex (18%). All 35 patients who attempted ETH (100%) had successful cooling, with a mean endovascular coronary reperfusion temperature of 33.1°C ± 0.9°C. The mean ischemic time was 375 ± 89.4 minutes in the hypothermia group and 359.5 ± 99.4 minutes in the control group. The mean DTB was 92.1 ± 20.5 minutes in the hypothermia group and 87 ± 24.4 minutes in the control group. The absolute difference of 5.1 minutes was not statistically significant (p = 0.509). The MACE rates were similar between both groups (21.7% vs. 20% respectively, p = 0.237). In the comparison between the hypothermia and control groups, no statistically significant differences were observed at 30 days between mean IS (13.9% ± 8% vs. 13.8% ± 10.8%, respectively, p = 0.801) and mean final LVEF (43.3% ± 11.2% vs. 48.3 ± 10.9%, respectively; p = 0.194). Hypothermia as an adjunctive therapy to primary PCI in STEMI is feasible and can be implemented without delay in coronary reperfusion. Hypothermia was safe regarding the incidence of MACE at 30 days. However, there was a higher incidence of arrhythmia and in-hospital infection in the hypothermia group, with no increase in mortality. Regarding efficacy, there was no difference in IS or LVEF at 30 days that would suggest additional myocardial protection with ETH. ClinicalTrials.gov: NCT02664194.