Search

To study the effect of plitidepsin antiviral treatment in immunocompromised COVID-19 patients with underlying haematological malignancies or solid tumours, particularly those who have undergone anti-CD20 therapies. We conducted a retrospective observational study, involving 54 adults treated with plitidepsin on compassionate use as an antiviral drug. Our analysis compared outcomes between patients with solid tumours and those with haematological malignancies, and a cohort of cases treated or not with anti-CD20 monoclonal antibodies. Patients with a history of anti-CD20 therapies showed a prolonged time-to-negative RT-PCR for SARS-CoV-2 infection compared to non-treated patients (33 d (28;75) vs 15 (11;25); p =.002). Similar results were observed in patients with solid tumours in comparison to those with haematological malignancies (13 (10;16) vs 26 (17;50); p <.001). No serious adverse events were documented. Patients with haematological malignancies appear to be at a heightened risk for delayed SARS-CoV-2 clearance and subsequent clinical complications. These findings support plitidepsin as a well-tolerated treatment in this high-risk group. A phase II clinical trial (NCT05705167) is ongoing to evaluate plitidepsin as an antiviral drug in this population. Haematological patients face an increased risk for severe COVID-19. Anti-CD20 therapies could increase fatal outcomes in COVID-19 patients. Persistent viral replication is increased in immunocompromised patients. Plitidepsin does not lead to new serious adverse events in immunocompromised patients. [ABSTRACT FROM AUTHOR]

Due to the COVID-19 global pandemic, computer-assisted diagnoses of medical images have gained much attention, and robust methods of semantic segmentation of Computed Tomography (CT) images have become highly desirable. In this work, we present a deeper analysis of how data augmentation techniques improve segmentation performance on this problem. We evaluate 20 traditional augmentation techniques on five public datasets. Six different probabilities of applying each augmentation technique on an image were evaluated. We also assess a different training methodology where the training subsets are combined into a single larger set. All networks were evaluated through a 5 -fold cross-validation strategy, resulting in over 4 , 600 experiments. We also propose a novel data augmentation technique based on Generative Adversarial Networks (GANs) to create new healthy and unhealthy lung CT images, evaluating four variations of our approach with the same six probabilities of the traditional methods. Our findings show that GAN-based techniques and spatial-level transformations are the most promising for improving the learning of deep models on this problem, with the StarGAN v2 + F with a probability of 0.3 achieving the highest F-score value on the Ricord1a dataset in the unified training strategy. Our code is publicly available at . [ABSTRACT FROM AUTHOR]