Diagnosis of COVID-19 from Chest X-rays Using CNN and Determination of Its Severity by Text Analysis

In India, the effect of COVID-19 has been worst because of various reasons like huge population, lack of necessary medical infrastructure, lack of awareness among people, inability to identify people with actual severe conditions and many more. Some people are waiting for more than a day to get the test results besides having rapid diagnosing kits. Due to a lack of awareness among people, patients with mild conditions are joining hospitals, leaving no place for severely infected patients. There is a need to automate the diagnosis of COVID-19 and identify the people with actual severe conditions so that those patients can be equipped with the required medical infrastructure and can potentially stop the process of spreading the disease and can even reduce the mortality rate. This need motivated us to propose a model which can diagnose COVID-19 and detect patients with severe conditions. Chest X-rays of individuals are efficient and can be used for rapid diagnosis of COVID-19 as X-ray centers are available even at rural areas. The proposed system automates the detection of COVID-19 and distinguishes the COVID-19 cases from other pneumonia and normal cases using a 11-layer Convolution Neural Network (CNN) model. We can use text analysis techniques on the patient's health condition which can be obtained by collecting details of the patient like age, body temperature, need for supplementary oxygen requirement, etc., we can identify the severity of the disease. The proposed CNN model achieved a 0.84 accuracy and on test data. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Deep Learning Approach Using 3D-ImpCNN Classification for Coronavirus Disease

Coronavirus (COVID-19) is a disease which is spreading rapidly, and nearly 1,436,000 people have been infected in about 200 countries all over the world as of April 2020. It is essential to detect COVID-19 at the earliest stage to care for the infected patients and, moreover, to prevent spreading and protect uninfected people. Deep learning approach, namely, convolutional neural networks (CNNs), requires extensive training data. Due to the recent epidemic, collecting enormous radiographic images in a very short duration is a challenging task. The major issues toward the success of CNN approach is the smaller dataset. Training dataset is scaled, and the results of detecting COVID-19 are boosted by using the proposed 3D-ImpCNN approach. This paper introduces 3D_ImpCNN classification model to categorize the patient affected by COVID. The COVID-19 classification outcomes of the method introduced is analyzed which produced better results when compared against existing methods. Accuracy of 3D-ImpCNN classification method was 96.5%, and moreover this method assists in detecting COVID-19 in a rapid manner. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.