The Coronavirus Disease 2019 (COVID-19) which first emerged in Wuhan, China in late December, 2019, has now spread to all the countries in the world. Conventional testing methods such as the antigen test, serology tests, and polymerase chain reaction tests are widely used. However, the test results can take anything from a few hours to a few days to reach the patient. Chest CT scan images have been used as alternatives for the detection of COVID-19 infection. Use of CT scan images alone might have limited capabilities, which calls attention to incorporating clinical features. In this paper, deep learning algorithms have been utilized to integrate the chest CT scan images obtained from patients with their clinical characteristics for fast and accurate diagnosis of COVID-19 patients. The framework uses an ANN to obtain the probability of the patient being infected with COVID-19 using their clinical information. Beyond a certain threshold, the chest CT scan of the patient is classified using a deep learning model which has been trained to classify the CT scan with 99% accuracy.
The COVID-19 pandemic first originated in Wuhan, China and has spread to every country in the world. Without a viable cure in the near future, there is an urgent need for rapid diagnosis of COVID-19, faster test results and automated segmentation of infected region in the lungs. The aim of this paper is to assist in the rapid detection and segmentation of COVID-19 patients using deep learning techniques. This paper proposes a method for automatic segmentation of the lung and infected regions of COVID 19 patients using lung CT scan dataset. This has been done using a modified U-Net model along with different cross validation folds. The region of infection which is segmented will contain the lesion, which if identified in the early stages can be beneficial during treatment of the person. This can help doctors to determine the severity of the infection and suggest treatments based on it. A comparative analysis of the proposed architectures has been done against recently published results which proves the superiority of our models in terms of dice similarity coefficients.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.