Automatic segmentation and measurement of the lungs in healthy persons and in patients with chronic obstructive pulmonary disease in CT images

Abstract

Nowadays, Computed Tomography (CT) of the thorax is the most accurate image technique for the diagnosis of the majority of the lung and chest diseases. Despite of this fact there are still limitations of CT in diagnosing and specially quantifying lung diseases such as emphysema. The automatic segmentation and measurement of the lungs and thoracic structures can improve by image processing techniques. These techniques enhance the visualization of the lungs and the chest wall. The present paper presents a method of automatic classification capable to segment and measure the lungs and the thoracic cavity both in healthy volunteers and in patients with Chronic Obstructive Pulmonary Disease (COPD) in prone positions based on technique of region growing. With the region growing method, based on computer programs, it is possible to segment and measure the aerated lung and the thoracic cavity. © Springer-Verlag Berlin Heidelberg 2007.