A comparative analysis of eleven neural networks architectures for small datasets of lung images of COVID-19 patients toward improved clinical decisions.

The 2019 novel severe acute respiratory syndrome coronavirus 2-SARS-CoV2, commonly known as COVID-19, is a highly infectious disease that has endangered the health of many people around the world. COVID-19, which infects the lungs, is often diagnosed and managed using X-ray or computed tomography (CT) images. For such images, rapid and accurate classification and diagnosis can be performed using deep learning methods that are trained using existing neural network models. However, at present, there is no standardized method or uniform evaluation metric for image classification, which makes it difficult to compare the strengths and weaknesses of different neural network models. This paper used eleven well-known convolutional neural networks, including VGG-16, ResNet-18, ResNet-50, DenseNet-121, DenseNet-169, Inception-v3, Inception-v4, SqueezeNet, MobileNet, ShuffeNet, and EfficientNet-b0, to classify and distinguish COVID-19 and non-COVID-19 lung images. These eleven models were applied to different batch sizes and epoch cases, and their overall performance was compared and discussed. The results of this study can provide decision support in guiding research on processing and analyzing small medical datasets to understand which model choices can yield better outcomes in lung image classification, diagnosis, disease management and patient care.

Impact of COVID-19 on advanced dental education: Perspectives of dental residents in Wuhan.

PURPOSE: This study investigated the impact of coronavirus disease 2019 (COVID-19) from the perspectives of dental residents in Wuhan, the former COVID-19 epicenter of China. METHODS: A survey form was sent to 424 residents in the School of Stomatology, Wuhan University (WHUSS) in September 2020. The form included 23 questions on demographics, study situation of residents during the COVID-19 outbreak, effect of COVID-19 on graduates, and status of residents who returned to clinic training. RESULTS: A total of 361 (85%) survey forms were collected. Over 70% of respondents felt anxious during Wuhan lockdown. Most respondents continued studying (94%) mainly through free online resources (79%). The majority reported improvement in didactic knowledge (80%), but the respondents' perceptions of their clinical skills, especially those in Wuhan, did not change (41%) or worsened (40%) (p < 0.05). Most graduates (88%) reported having found jobs or continued study. Among the 209 responders who returned to clinical training, 52% felt no concern about COVID-19 infection, 89% thought they were equipped with adequate personal protective equipment (PPE), and 57% indicated that they received sufficient knowledge for preventing COVID-19 in clinic. Most respondents agreed that the way to gain the knowledge for preventing COVID-19 in clinic was training at dental school (93%). CONCLUSION: Although online study has been appreciated by residents, concern about clinical skill learning in the COVID-19 hardest-hit area has arisen. Most graduates felt that the impact of COVID-19 on their immediate postgraduation career was limited. Teaching about infection control in dental schools seemed effective to develop a positive attitude for residents after they returned to clinical training.