Classification and Detection of Coronavirus in Lung Images using Random Forests Algorithm

Abstract

Coronavirus 2019 (COVID-19), which emerged in Wuhan, China and affected the whole world, has cost the lives of thousands of people. Manual diagnosis is inefficient due to the rapid spread of this virus. For this reason, automatic COVID-19 detection studies are carried out with the support of Random forest algorithms. A research datasets consists 794 CT image slices was used to validate our proposed method. In this thesis, Firstly The pre-process done using filter to remove speckle noise and enhance the image as general. Then alveoli and COVID-19 segmentation are performed to be extracted from abdominal CT image using clustering texture (K-mean clustering) method. Secondly, texture feature information provided by GLCM is expected to differentiate between normal and abnormal tissue. Finally, COVID-19 detection is done on the segmented lung image using RF classifier, all the mentioned algorithm used in this project are robust and accurate more than the human visual system. The result of proposed system 97.25% accuracy in distinguishing between normal alveoli and COVID-19.