This paper shows a method for extracting bronchus region from 3D chest CT images. Several research groups have proposed methods for extracting bronchus regions by using region growing algorithm. However, these methods do not work well in the case that tumors divide the bronchus region into several parts. Therefore, this study proposes a method that can extract the bronchus region in such cases using local intensity structure analysis, CT value distribution and shape features for extracting the bronchus region. First, the proposed method extracts cylindrical structure by using hessian matrix to analyze local intensity structure. Second, this method extracts tube structure by use modified RRF to analyze CT value distribution and shape features. Finally, this method extracts the bronchus region by integrating regions extracted by RRF and hessian matrix. We applied the proposed method to four 3D chest CT images. Experimental result shows that the proposed method can extract bronchus regions in the case that tumors divide the bronchus region into several parts.     «

This paper shows a method for extracting bronchus region from 3D chest CT images. Several research groups have proposed methods for extracting bronchus regions by using region growing algorithm. However, these methods do not work well in the case that tumors divide the bronchus region into several parts. Therefore, this study proposes a method that can extract the bronchus region in such cases using local intensity structure analysis, CT value distribution and shape features for extracting the b...     »