The auto-segmentation algorithm for pulmonary parenchyma of CT image based on linear filtration

A novel algorithm is proposed in this paper in terms of the existing segmentation algorithm for pulmonary parenchyma of computed tomography (CT) image lacking automation. The images from blood vessels, bone, liver, heart and muscle composition on thoracic CT is characterized by great width and high gray-level, considering that, the proposed algorithm uses linear filtering to extract the outline of high gray-level region mixed. And then mathematic morphology and horizontal scanning algorithm is employed for automatic segmentation of pulmonary parenchyma region on thoracic CT. Experiment on 100 cases of thoracic CT demonstrates that the ratio of automatic segmentation reaches up to 96%, and the results are accurate and encouraging.