An efficient Covid-19 detection and severity analysis using optimized mask region-based convolution neural network

Abstract

Coronavirus 2019 (COVID-19) is a severe disease in respiratory syndrome. Early identification and efficient treatment of COVID-19 are not presented which provides ineffective treatment. This research develops an efficient system for early detection and segmentation of COVID-19 severity with the consideration of CT images. To overcome the abovementioned drawbacks, we develop the optimized Mask R-CNN method to train and test the dataset to classify and segment the COVID-19 disease. The proposed technique contains three phases which are, pre-processing, segmentation, and severity analysis. Initially, the patient’s CT images are collected from a different clinic. Then, the noise present in the images is detached with a Gaussian filter. Then, the pre-processed images are given to the optimized mask region-based convolution neural network (OMRCNN) classifier to detect, classify and segment the image. After segmentation, the severity of the disease is examined. To enhance the performance of the mask RCNN classifier, the parameter is efficiently chosen by using the adaptive red deer algorithm. In the adaptive red deer algorithm, the levy flight is utilized to enhance the updating process. The performance of the proposed technique is analyzed based on various metrics.