Deep CNN-WCA and FLICM image segmentation for automatic detection and classification of COVID-19 Diseases

Abstract

COVID-19 is the leading cause for unknown deaths in men in age 60 to 90 and also women in same age group. Now a days the all age groups are also affected by COVID-19 diseases. Diagnosis of COVID-19 diseases is a very important part in its treatment. A prime reason behind an increase in the number of cancer patients worldwide is the ignorance of people towards treatment in its early stages. This research work proposes a novel Fuzzy Local Information C  Means  (FLICM) segmentation technique for detection of tissues from COVID-19 image that can inform the radiologist and doctor about the details of diseased tissues. This segmentation technique include noise removal and sharpening of the image along with basic morphological functions, erosion and dilation, to obtain the background. The segmented images are applied to the proposed Deep CNN-WCA (Convolutional neural network with water cycle algorithm) classification of the type of diseased tissues for visual localization. Further the classification results will be compared with the existing conventional CNN with back propagation model.