Lung And Chest Wall Structures Segmentation In Ct Images

Computed Tomography (CT) of thorax is nowadays the most accurate image technique for diagnosis of the majority of lung and chest diseases. Despite this fact there are still limitations of CT in diagnosing and specially quantifying lung diseases such as Chronic Obstructive Pulmonary Disease (COPD). The present paper presents a method of automatic classification capable to segment the lungs and the chest wall elements in patients with COPD in supine and prone positions. The technique of binary mathematical morphology was used to segment the lungs and the thoracic cavity using region growing following for negative this image. The lungs, the thoracic cavity and the pulmonary vessels were all successfully segmented with the application of the mathematical morphology and region growing. This method of processing CT images may be a promising tool for qualitative and quantitative studies of chest CT images.