Extraction and assessment of COVID19 infection in lung CT images using VGG-UNet

The infectious disease in humans is gradually rising for various reasons, and COVID19 is one of the recently discovered diseases caused by SARS-CoV-2. From early 2020, the infection due to COVID19 has gradually increased, and still, its infection exists. COVID19 will cause severe infection in the respiratory tract, and early detection and treatment are essential. The harshness of the infection needs to be examined before implementing the treatment. This research aims to build up and implement a suitable procedure to extract and assess the infected section in lung CT slices. This work extracts the infected section using the pre-trained VGG-UNet scheme. The separated section is validated against the ground-truth (GT) image, and the necessary presentation standards are calculated. The performance of the VGG-UNet is then compared and verified with the UNet and UNet+ schemes. The investigational product of this study authenticate that the effect reached with the proposed study confirms that the VGG-UNet provides better Jaccard, Dice and accuracy compared to UNet and UNet+.

Performance analysis of lightweight CNN models to segment infectious lung tissues of COVID-19 cases from tomographic images.

The pandemic of Coronavirus Disease-19 (COVID-19) has spread around the world, causing an existential health crisis. Automated detection of COVID-19 infections in the lungs from Computed Tomography (CT) images offers huge potential in tackling the problem of slow detection and augments the conventional diagnostic procedures. However, segmenting COVID-19 from CT Scans is problematic, due to high variations in the types of infections and low contrast between healthy and infected tissues. While segmenting Lung CT Scans for COVID-19, fast and accurate results are required and furthermore, due to the pandemic, most of the research community has opted for various cloud based servers such as Google Colab, etc. to develop their algorithms. High accuracy can be achieved using Deep Networks but the prediction time would vary as the resources are shared amongst many thus requiring the need to compare different lightweight segmentation model. To address this issue, we aim to analyze the segmentation of COVID-19 using four Convolutional Neural Networks (CNN). The images in our dataset are preprocessed where the motion artifacts are removed. The four networks are UNet, Segmentation Network (Seg Net), High-Resolution Network (HR Net) and VGG UNet. Trained on our dataset of more than 3,000 images, HR Net was found to be the best performing network achieving an accuracy of 96.24% and a Dice score of 0.9127. The analysis shows that lightweight CNN models perform better than other neural net models when to segment infectious tissue due to COVID-19 from CT slices.