Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

T. Kitasaka, H. Yano, M. Feuerstein, K. Mori
Bronchial region extraction from 3D chest CT image by voxel classification based on local intensity structure
Third International Workshop on Pulmonary Image Analysis, September 2010 (bib)

This paper presents a method for extracting bronchial regions from 3D chest CT images by voxel classification based on local intensity structure. Most of previous methods are based on trace of bronchial tree structures by region growing algorithms, so that it fails when the bronchial lumen is interrupted by abnormals such as tumor. Thus, we focus on detecting candidate voxels which have bronchus-like intensity structure and selecting appropriate candidates from them, instead of tracing the bronchial tree, int bronchial region extraction. Two types of tube enhancement filters are employed in our algorithm. One is designed to enhance bronchus-like intensity structure where low intensity regions are surrounded by higher intensity regions and cross section of a bronchus along its running direction forms the circular shape. The other filter is utilized to enhance line structures based on the Hessian matrix analysis. The experimental results for eight cases of 3D chest CT images showed that the accuracy of the proposed method improved by 10 % compared with a previous method, while FPs increased relatively.
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Edit | Attach | Refresh | Diffs | More | Revision r1.13 - 30 Jan 2019 - 15:16 - LeslieCasas

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif