Detection of COVID-19 from CT scan images using deep neural networks

The coronavirus pandemic brought the world to a standstill of historic significance. Countries over the world have imposed lockdowns, quarantines and travel bans in an effort to stop the further spread of the disease. Healthcare systems worldwide are under extreme pressure due to the influx of a large amount of patients suffering from COVID-19. Moreover, there is a dearth of doctors, nurses, and support staff in hospitals of many countries. In such a predicament, it is imperative to leverage the advances made in computer vision and deep learning technologies to create a system that attempts to ease the burden on worldwide healthcare. In this research, ten state-of-the-art pre-trained convolutional neural networks were used to identify COVID-19 in chest Computed Tomography (CT) scan images. After extensive experimental testing and tuning, comprehensive comparative analysis was done and very promising results were obtained in this classification task. © 2021 IEEE

Transfer Learning-Based Detection of Covid-19 Using Chest CT Scan Images

The global pandemic caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) virus has had historical impact on the world. The virus causes severe respiratory problems and with an R0 of 5.7, spreads at a rapid rate. At the time of writing, there were over 85 million cases and 1.8 million deaths caused by COVID-19. In the proposed methodology, Deep Convolutional Neural Networks (DCNNs) have been trained, with the help of transfer learning, to learn to identify whether a suspected patient is suffering from this disease using their chest CT scan image. Transfer learning technique enables the transfer of knowledge from pre-trained models which have been previously trained on extremely large datasets. Various DCNN models have been applied such as AlexNet, ResNet-18, ResNet-34, ResNet-50, VGG-16, and VGG-19. The DCNNs were evaluated on a set of 2,481 chest CT scan images. Various performance metrics (Accuracy, MCC, Kappa, F1 score, etc.) were calculated for all DCNN models to enable their comparative evaluation. After extensive testing, ResNet50 was found to give the best results in this binary classification task. The highest accuracy achieved was 97.37% and highest kappa was 0.947. Identification of presence of COVID-19 using this method would provide great benefit to society and mankind. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.