No abstract

Background and objectives:COVID-19 related inflammation, endothelial dysfunction and coagulopathy may increase the bleeding risk and lower efficacy of revascularization treatments in patients with acute ischemic stroke. We aimed to evaluate the safety and outcomes of revascularization treatments in patients with acute ischemic stroke and COVID-19.Methods:Retrospective multicenter cohort study of consecutive patients with acute ischemic stroke receiving intravenous thrombolysis (IVT) and/or endovascular treatment (EVT) between March 2020 and June 2021, tested for SARS-CoV-2 infection. With a doubly-robust model combining propensity score weighting and multivariate regression, we studied the association of COVID-19 with intracranial bleeding complications and clinical outcomes. Subgroup analyses were performed according to treatment groups (IVT-only and EVT).Results:Of a total of 15128 included patients from 105 centers, 853 (5.6%) were diagnosed with COVID-19. 5848 (38.7%) patients received IVT-only, and 9280 (61.3%) EVT (with or without IVT). Patients with COVID-19 had a higher rate of symptomatic intracerebral hemorrhage (SICH) (adjusted odds ratio [OR] 1.53; 95% CI 1.16–2.01), symptomatic subarachnoid hemorrhage (SSAH) (OR 1.80; 95% CI 1.20–2.69), SICH and/or SSAH combined (OR 1.56; 95% CI 1.23–1.99), 24-hour (OR 2.47; 95% CI 1.58–3.86) and 3-month mortality (OR 1.88; 95% CI 1.52–2.33).COVID-19 patients also had an unfavorable shift in the distribution of the modified Rankin score at 3 months (OR 1.42; 95% CI 1.26–1.60).Discussion:Patients with acute ischemic stroke and COVID-19 showed higher rates of intracranial bleeding complications and worse clinical outcomes after revascularization treatments than contemporaneous non-COVID-19 treated patients. Current available data does not allow direct conclusions to be drawn on the effectiveness of revascularization treatments in COVID-19 patients, or to establish different treatment recommendations in this subgroup of patients with ischemic stroke. Our findings can be taken into consideration for treatment decisions, patient monitoring and establishing prognosis.

No abstract

Proliferative diabetic retinopathy (PDR) is an advanced diabetic retinopathy stage, characterized by neovascularization, which leads to ocular complications and severe vision loss. However, the available DRlabeled retinal image datasets have a small representation of images of the severest DR grades, and thus there is lack of PDR cases for training DR grading models. Additionally, the criteria for labelling these images in the publicly available datasets is not always clear, with some images which do not show typical PDR lesions being labeled as PDR due to the presence of photo-coagulation treatment and laser marks. This problem, together with the datasets' high class imbalance, leads to a limited variability of the samples, which the typical data augmentation and class balancing cannot fully mitigate. We propose a heuristicbased data augmentation scheme based on the synthesis of neovessel (NV)-like structures that compensates for the lack of PDR cases in DR-labeled datasets. The proposed neovessel generation algorithm relies on the general knowledge of common location and shape of these structures. NVs are generated and introduced in pre-existent retinal images which can then be used for enlarging deep neural networks' training sets. The data augmentation scheme was tested on multiple datasets, and allows to improve the model's capacity to detect NVs.

No abstract