Robust region growing based intrathoracic airway tree segmentation
Faculty of Sciences. Physics
S.l. , 2009
Proceedings of The Second International Workshop on Pulmonary Image Analysis, London, UK, September, 2009
University of Antwerp
In this paper, we present a semi-automatic region growing algorithm to segment the intrathoracic airway tree from 3-d CT images. A common problem with region growing is leakage. In order to limit leakage, our method bounds the segmentation using cylinders of adaptive orientation and dimensions. The leaks are detected based on anatomical information of the airways and an algorithm to avoid them is proposed. We also present an algorithm to automatically select a seed point for the segmentation. The method was tested on a dataset of 40 patients and results were quantitatively evaluated based on ground truth data.