Improving COVID-19 CT Classification of CNNs by Learning Parameter-Efficient Representation (preprint)

COVID-19 pandemic continues to spread rapidly over the world and causes a tremendous crisis in global human health and the economy. Its early detection and diagnosis are crucial for controlling the further spread. Many deep learning-based methods have been proposed to assist clinicians in automatic COVID-19 diagnosis based on computed tomography imaging. However, challenges still remain, including low data diversity in existing datasets, and unsatisfied detection resulting from insufficient accuracy and sensitivity of deep learning models. To enhance the data diversity, we design augmentation techniques of incremental levels and apply them to the largest open-access benchmark dataset, COVIDx CT-2A. Meanwhile, similarity regularization (SR) derived from contrastive learning is proposed in this study to enable CNNs to learn more parameter-efficient representations, thus improving the accuracy and sensitivity of CNNs. The results on seven commonly used CNNs demonstrate that CNN performance can be improved stably through applying the designed augmentation and SR techniques. In particular, DenseNet121 with SR achieves an average test accuracy of 99.44% in three trials for three-category classification, including normal, non-COVID-19 pneumonia, and COVID-19 pneumonia. And the achieved precision, sensitivity, and specificity for the COVID-19 pneumonia category are 98.40%, 99.59%, and 99.50%, respectively. These statistics suggest that our method has surpassed the existing state-of-the-art methods on the COVIDx CT-2A dataset.

Analysis of the Mental Health Status of University students after the COVID-19 Epidemic (preprint)

Objective The aim of this study was to investigate the mental health status and sleep quality of university students after local outbreak of COVID-19, and to help them understand the psychological stress reaction and provide base for their mental health education. Methods A cross-sectional survey was conducted on the mental health status of university students in a Wuhan-based university. Results A total of 897 university students were enrolled in the study. Compared with the epidemic period, university students' mental health status and sleep quality has a great deal of difference in the aspects of gender, grade, discipline and specialty, physical exercise, as well as with their family relationships and so on. 64.26% students would like to talk to their peers or close friends, while only 2.71% would like to call a caring hotline or seek help from a psychologist. Conclusion After the local outbreak of COVID-19 in Wuhan was contained, the mental health status and sleep quality of more than half of the students improved. However, priority attention and care should be given to female students, senior students, those undertaking literature and history majors and those dissatisfied with family relationships.