Reliable airway tree segmentation based on hole closing in bronchial walls

Abstract

Reliable segmentation of a human airway tree from volumetric computer tomography (CT) data sets is the most important step for further analysis in many clinical applications such as diagnosis of bronchial tree pathologies. In this paper the original airway segmentation algorithm based on discrete topology and geometry is presented. The proposed method is fully automated, reliable and takes advantage of well defined mathematical notions. Holes occur in bronchial walls due to many reasons, for example they are results of noise, image reconstruction artifacts, movement artifacts (heart beat) or partial volume effect (PVE). Holes are common problem in previously proposed methods because in some areas they can cause the segmentation algorithms to leak into surrounding parenchyma parts of a lung. The novelty of the approach consists in the application of a dedicated hole closing algorithm which closes all disturbing holes in a bronchial tree. Having all holes closed the fast region growing algorithm can be applied to make the final segmentation. The proposed method was applied to ten cases of 3D chest CT images. The experimental results showed that the method is reliable, works well in all cases and generate good quality and accurate results.