COVID-19 Lung CT Image Segmentation Using Deep Learning Methods: UNET Vs. SegNET

Abstract Background: Currently, there is an urgent need for efficient tools to assess the diagnosis of COVID-19patients. In this paper, we present feasible solutions for detecting and labeling infected tissues on CT lungimages of such patients. Two structurally-different deep learning techniques, SegNet and UNET, areinvestigated for semantically segmenting infected tissue regions in CT lung images.Methods: We propose to use two known deep learning networks, SegNet and UNET, for image tissueclassification. SegNet is characterized as as scene segmentation network and UNET as a medical segmentationtool. Both networks were exploited as binary segmentors to discriminate between infected and healthy lungtissue, also as multi-class segmentors to learn the infection type on the lung. Each network is trained usingseventy-two data images, validated on ten images, and tested against the left eighteen images. Severalstatistical scores are calculated for the results and tabulated accordingly.Results: The results show the superior ability of SegNet in classifying infected/non-infected tissues comparedto the other methods (with 0:95 mean accuracy), while the UNET shows better results as a multi-classsegmentor (with 0:91 mean accuracy).Conclusion: Semantically segmenting CT scan images of COVID-19 patients is a crucial goal because it wouldnot only assist in disease diagnosis, also help in quantifying the severity of the illness, and hence, prioritize thepopulation treatment accordingly. We propose computer-based techniques that prove to be reliable asdetectors for infected tissue in lung CT scans. The availability of such a method in today’s pandemic wouldhelp automate, prioritize, fasten, and broaden the treatment of COVID-19 patients globally.