A Neoteric Segmentation Approach for Lung Ultrasound Images

The global surge in reported cases of COVID-19 and the possibility of further outbreaks necessitates the development of new instruments to aid healthcare professionals in the earlier detection and monitoring of patients. Lung Ultrasound (LUS) examination is increasingly being used to detect symptoms of COVID-19 disease, according to growing data from throughout the world. Numerous features of ultrasound imaging make it well-suited for frequent clinical application: LUS may identify lung participation in the initial stages of the disease, is portable enough to be carried around in a protective covering, and can be used for screening in long-term care residences, camps, and other settings out of the clinic when other imaging techniques are not possible. The purpose of this article is to segment the COVID region from LUS. Acquiring LUS image data is the first step in the research workflow, which concludes with validating the segmented model. The COVID region is separated from the LUS region through the use of several pre-processes, including filtering and image enhancement, and the development of a segmentation model, including threshold, region-based, edge-based, and a neoteric segmentation approach. To choose the most effective model, we use the model accuracy.