HYBRID ALGORITHM FOR DETECTION OF COVID-19 FROM CT SCANS AND X-RAYS

Abstract: Detecting COVID-19 is a difficult task for medical professionals these days due to its rapid spread. To overcome this problem, various techniques and detection methods to control the spread of COVID-19 are used. CT (Computed Tomography) Scan and X rays are currently used in the detection of COVID-19. This type of diagnostic method is accurate and fast and can be used along with normal covid-19 testing methods. The normal covid-19 testing methods such as RT-PCR method requires a radiologist to detect the disease. Therefore, it is important to implement a system to detect the corona virus automatically as an alternate quickly. This is intended to help doctors detect computed tomography (CT) images and X-Ray images of patient’s lungs infected with COVID-19. In this proposed system a Deep Learning algorithm which uses four Convolutional Neural Network (CNN) models: InceptionV3, ResNet50, Xception and VGG16 are used. These convolutional neural network models are pre-trained and we used the dataset obtained from open source which contains CT scans and X-Rays to retrain the model for the detection of Covid-19. The combined models are used for the prediction of images given by the user in a web-based prediction method. Thus, the suggested hybrid algorithm is effective for predicting images as covid or non-covid.

Keywords: Hybrid Model, CT scans and X-rays, Deep Learning Model, and CNN.