Deep Neural Network models for diagnosis of COVID-19 Respiratory diseases by analyzing CT-Scans and Explainability using trained models
Abstract— The Novel Coronavirus, popularly known as "COVID-19," is causing a devastating viral epidemic over the world. This virus causes severe respiratory disease in those who are afflicted. Symptoms such as fever, dry cough, and exhaustion can be used to identify this virus, however these symptoms are similar to those of other viral or respiratory diseases. There is no rapid way to determine whether or not an individual is exposed to the virus. To counter the abovementioned constraints, a quicker diagnosis is desired, which brings us to the study's goal: to develop a diagnostic approach that incorporates previous data, mostly from COVID-19, as well as datasets from other respiratory disorders. We'll utilize deep learning models to assess the datasets we've collected, allowing us to get more accurate and efficient findings. CNN models such as VGG19, Inception v3, MobileNetV2, and ResNet-50 are among the Deep Neural Network models we plan to deploy. These four models have been pre-trained to categorize CT-Scan images using trained learning methodologies. To obtain faster and more accurate answers, the outcomes of each model are compared among the models. A "Hybrid" model built of CNN and a Support Vector Machine (SVM) is also proposed in this research. The Hybrid Model is not as deep as the pre-trained models, but it is as accurate. We will be able to diagnose more correctly and effectively based on the correctness of the outcome and the shortest time necessary for categorization of images which will enable us to diagnose more accurately and effectively.