RESUMEN
The global extent of COVID-19 mutations and the consequent depletion of hospital resources highlighted the necessity of effective computer-assisted medical diagnosis. COVID-19 detection mediated by deep learning models can help diagnose this highly contagious disease and lower infectivity and mortality rates. Computed tomography (CT) is the preferred imaging modality for building automatic COVID-19 screening and diagnosis models. It is well-known that the training set size significantly impacts the performance and generalization of deep learning models. However, accessing a large dataset of CT scan images from an emerging disease like COVID-19 is challenging. Therefore, data efficiency becomes a significant factor in choosing a learning model. To this end, we present a multi-task learning approach, namely, a mask-guided attention (MGA) classifier, to improve the generalization and data efficiency of COVID-19 classification on lung CT scan images. The novelty of this method is compensating for the scarcity of data by employing more supervision with lesion masks, increasing the sensitivity of the model to COVID-19 manifestations, and helping both generalization and classification performance. Our proposed model achieves better overall performance than the single-task (without MGA module) baseline and state-of-the-art models, as measured by various popular metrics.
RESUMEN
BACKGROUND: Liver transplantation is a proven management method for end-stage cirrhosis and is estimated to have increased life expectancy by 15 years. The COVID-19 pandemic posed a challenge to patients who were candid for a solid-organ transplant. It has been suggested that the outcomes of liver transplants could be adversely affected by the infection, as immunosuppression makes liver transplant candidates more susceptible to adverse effects while predisposing them to higher thrombotic events. MATERIAL AND METHODS: In this retrospective study, the cases who received liver transplants from January 2018 to March 2022 were assessed regarding early postoperative mortality rate and hepatic artery thrombosis (HAT) with COVID-19 infection. This study included 614 cases, of which 48 patients were infected. RESULTS: This study shows that the early COVID-19-related early postoperative mortality rates substantially increased in the elective setting (OR: 2.697), but the results for the acute liver failure were insignificant. The average model for end-stage liver disease score increased significantly during the pandemic due to new regulations. Although mortality rates increased during the pandemic, the data for the vaccination period show that mortality rates have equalised with the prepandemic era. Meanwhile, COVID-19 infection is assumed to have increased HAT by 1.6 times in the elective setting. CONCLUSION: This study shows that COVID-19 infection in an acute liver failure poses comparatively little risk; hence transplantation should be considered in such cases. Meanwhile, the hypercoagulative state induced by the infection predisposes this group of patients to higher HAT rates.