• About Us
• Education
• Research
• PhD
• Acta Cybernetica
• Conferences
• Sponsors

• - Applied Informatics
• - Image Processing and Computer Graphics
• - Foundations of Computer Science
• - Computer Algorithms and Artificial Intelligence
• - Software Engineering
• - Research Group on Artificial Intelligence

Quantitative analysis of tubular tree structures

Members: Kálmán Palágyi Funded by NIH R01 HL-064368 Partners: Milan Sonka (The University of Iowa) Related Projects: 3D Thinning Algorithms Assessment of tracheal stenoses, infra-renal aortic aneurysms, and colorectal polyps Thinning algorithms based on sufficient conditions for topology preservation Lifetime: 2002 - 2006

Description

Tubular structures are frequently found in living organisms. The tubes — e.g., arteries or veins — are organized into more complex structures. Trees consisting of tubular segments form the arterial and venous systems, intrathoracic airways form bronchial trees, and other examples can be found.

Computed tomography (CT) or magnetic resonance (MR) imaging provides volumetric image data allowing identification of such tree structures. Frequently, the trees represented as contiguous sets of voxels must be quantitatively analyzed. The analysis may be substantially simplified if the voxel-level tree is represented in a formal tree structure consisting of a set of nodes and connecting arcs. To build such formal trees, the voxel-level tree object must be transformed into a set of interconnected single-voxel centerlines representing individual tree branches. Therefore, the aim of our work was to develop a robust method for identification of centerlines and bifurcation (trifurcation, etc.) points in segmented tubular tree structures acquired in vivo from humans and animals using volumetric CT or MR scanning, rotational angiography, or other volumetric imaging means.

Our method allows to quantitatively analyze tubular tree structures. Assuming that an imperfectly segmented tree was obtained from volumetric data in the previous stages, the presented technique allows to obtain a single-voxel skeleton of the tree while overcoming many segmentation imperfections, yields formal tree representation, and performs quantitative analysis of individual tree segments on a tree-branch basis. The input of the proposed method is a 3D binary image representing a segmented voxel-level tree object. All main components of our method were specifically developed to deal with imaging artifacts typically present in volumetric medical image data. As such, the method consists of the following main steps: (1) airway segmentation, (2) correction of the segmented tree, (3) identification of the tree root, (4) extraction of the 3D centerline—skeletonization, (5) tree pruning, (6) centerline smoothing, (7) identification of branch-points, (8) generation of a formal tree structure, (9) tree partitioning, and (10) quantitative analysis.

The key steps are now illustrated:

Segmentation - adaptive region growing (left), extracting centerlines - topologically and geometrically correct thinning (middle), and excluding branch-areas based on 3D distance map calculation (right).

Partitioning centerlines in a formal tree data structure (left), partitioning segmented tree via isotropic label propagation (middle), and quantitative analysis formal XML tree with associated measurements (right).

Publications

1. Kálmán Palágyi, Juerg Tschirren, Eric A. Hoffman, and Milan Sonka. Quantitative analysis of pulmonary airway tree structure. Computers in Biology and Medicine, 36:974-996, 2006. [PDF]
2. Juerg Tschirren, Geoffrey McLennan, Kálmán Palágyi, Eric A. Hoffman, and Milan Sonka. Matching and anatomical labeling of human airway tree. IEEE Transactions on Medical Imaging, 24:1540-1547, 2005. [PDF]
3. Eric A. Hoffman, Joseph M. Reinhardt, Milan Sonka, Brett A. Simon, Junfeng Guo, Osama Saba, Deokiee Chon, Shaher Samrah, Hidenori Shikata, Juerg Tschirren, Kálmán Palágyi, Kenneth C. Beck, and Geoffrey McLennan. Characterization of the Interstitial Lung Diseases via Density-Based and Texture-Based Analysis of Computed Tomography Images of Lung Structure and Function. Academic Radiology, 10:1104-1118, 2003. [PDF]
4. Reinhard Beichel, Thomas Pock, Christian Janko, Roman Zotter, Bernhard Reitinger, Alexander Bornik, Kálmán Palágyi, Erich Sorantin, Georg Werkgartner, Horst Bischof, and Milan Sonka. Liver segment approximation in CT data for surgical resection planning. In Medical Imaging 2004: Image Processing, Proceedings of SPIE, volume 5370, pages 1435-1446, 2005. [PDF]
5. Kálmán Palágyi, Juerg Tschirren, Eric A. Hoffman, and Milan Sonka. Assessment of Intrathoracic Airway Trees: Methods and In Vivo Validation. In Proceedings of the Computer Vision and Mathematical Methods in Medical and Biomedical Image Analysis: ECCV 2004 Workshops CVAMIA and MMBIA, volume 3117 of Lecture Notes in Computer Science, pages 341-352, 2004. Springer Verlag. [PDF]
6. Kálmán Palágyi, Juerg Tschirren, and Milan Sonka. Quantitative analysis of intrathoracic airway trees: methods and validation. In Proceedings of the International Conference on Information Processing in Medical Imaging (IPMI), volume 2732 of Lecture Notes in Computer Science, pages 222-233, 2003. Springer Verlag. [PDF]
7. Kálmán Palágyi, Juerg Tschirren, and Milan Sonka. Quantitative analysis of three-dimensional tubular tree structures. In Medical Imaging 2004: Image Processing, Proceedings of SPIE, volume 5032, pages 277-287, 2003. [PDF]