Lung Parenchyma Segmentation Based on CT Images

Abstract

Novel Coronavirus targets the lung posing a serious threat to human health and causing huge social and economic losses. Extraction of lung parenchyma from CT images is an important step in the diagnosis of Novel Coronavirus. Therefore, accurate segmentation of lung parenchyma is highly significant for the diagnosis of disease. A lung parenchyma segmentation method based on OTSU and morphological operation is proposed. First of all, according to the CT image noise type, bilateral filtering is selected as preprocessing to filter out image noise. Then, binary images are obtained by the OTSU-based algorithm. Secondly, the residual interference of the trachea and blood vessels in the image is removed by morphological operation, and connected areas are marked and holes are filled. Finally, the original image is multiplied by the mask to obtain the lung parenchyma image. Experimental results show that this method can accurately segment lung parenchyma.