Recognition of bronchus in three-dimensional X-ray CT images with applications to virtualized bronchoscopy system

Abstract

In this paper we present a procedure to extract bronchus area from 3D chest X-ray CT images. Extraction of bronchus from chest X-ray CT images is of critical importance for both the computer aided detection of lung cancer and the virtual bronchoscopy system. This procedure consists of three major steps: 1) calculation of a start point for region growing; 2) determination of the optimum threshold value; and 3) final extraction of bronchus area with the optimum threshold value. The proposed procedure extracts the bronchus area by following the inside points of bronchus. A 3D region growing method, called the 3D painting algorithm, is developed to perform this. The position of a starting point for the 3D painting algorithm is selected in the trachea automatically by using the shape features of trachea. Also this procedure can search the optimum threshold value by using the information of bronchus shape. We applied this method to real three dimensional X-ray CT images and confirmed that it worked satisfactorily.