A New Segmentation Method for Lung HRCT Images

Image segmentation plays a crucial role in many medical imaging applications by automating or facilitating the delineation of anatomical structures and other regions of interest. The aim of this paper is to develop an accurate and reliable method for segmentation of lung HRCT images using a pixel-based approach. The proposed method combines traditional concepts, such as global-threshold segmentation, mathematical morphology, edge detection and noise reduction, with new ideas, such as performing geometrical computations to achieve the defined ROIs. Two different approaches are proposed and tested on 100 computed-tomography images. Noise tolerance of the algorithm is calculated considering several parameters and objective criteria. In addition, the image segmentation results were visually validated by radiologists.