An Effective Segmentation Approach for Lung CT Images Using Histogram Thresholding with EMD Refinement

Image segmentation is an important step in extracting information from medical images. Segmentation of pulmonary chest computed tomography (CT) images is a precursor to most pulmonary image analysis. The purpose of lung segmentation is to separate the voxels corresponding to lung tissue from the surrounding anatomy. This paper presents an automated CT lung image segmentation. The approach utilizes histogram-based thresholding with Earth Mover's Distance (HTEMD)-based refinement methods. The final segmented output is further refined by morphological operators. The performance of HTEMD is compared with Otsu's, K-Means, and histogram thresholding using fuzzy measures.