Covid-19 ct lung image segmentation using adaptive donkey and smuggler optimization algorithm

Abstract

COVID'19 has caused the entire universe to be in existential health crisis by spreading globally in the year 2020. The lungs infection is detected in Computed Tomography (CT) images which provide the best way to increase the existing healthcare schemes in preventing the deadly virus. Nevertheless, separating the infected areas in CT images faces various issues such as lowintensity difference among normal and infectious tissue and high changes in the characteristics of the infection. To resolve these issues, a newinf-Net (Lung Infection Segmentation Deep Network) is designed for detecting the affected areas from the CT images automatically. For the worst segmentation results, the Edge-Attention Representation (EAR) is optimized using Adaptive Donkey and Smuggler Optimization (ADSO). The edges which are identified by the ADSO approach is utilized for calculating dissimilarities. An IFCM (Intuitionistic Fuzzy C-Means) clustering approach is applied for computing the similarity of the EA component among the generated edge maps and Ground-Truth (GT) edge maps. Also, a Semi-Supervised Segmentation (SSS) structure is designed using the Randomly Selected Propagation (RP) technique and Inf-Net, which needs only less number of images and unlabelled data. Semi-Supervised Multi-Class Segmentation (SSMCS) is designed using a Bi-LSTM (Bi-Directional Long-Short-Term-memory), acquires all the advantages of the disease segmentation done using Semi Inf-Net and enhances the execution of multi-class disease labelling. The newly designed SSMCS approach is compared with existing U-Net++, MCS, and Semi-Inf-Net. factors such as MAE (Mean Absolute Error), Structure measure, Specificity (Spec), Dice Similarity coefficient, Sensitivity (Sen), and Enhance-Alignment Measure are considered for evaluation purpose.