Airway Segmentation, Skeletonization, and Tree Matching to Improve Registration of 3D CT Images with Large Opacities in the Lungs
In this work, we address the registration of pulmonary images, representing the same subject, with large opaque regions within the lungs, and with possibly large displacements. We propose a hybrid method combining alignment based on gray levels and landmarks within the same cost function. The landmarks are nodes of the airway tree obtained by specially developed segmentation and skeletonization algorithms. The former uses the random walker approach, whereas the latter exploits the minimum spanning tree constructed by the Dijkstra’s algorithm, in order to detect end-points and bifurcations. Airway trees from different images are matched by a modified best-first-search algorithm with a specially designed distance function. The proposed method was evaluated on computed-tomography images of subjects with acute respiratory distress syndrome, acquired at significantly different mechanical ventilation conditions. It achieved better results than registration based only on gray levels, but also better than hybrid registration using a standard airway-segmentation method.
KeywordsAcute Respiratory Distress Syndrome Minimum Span Tree Oriented Graph Ventilation Condition Airway Tree
The authors thank Colciencias for doctoral scholarships granted to D. Gómez Betancur and A. Morales Pinzón, and also for its support through the French-Colombian ECOS-NORD program C15M04 grant. This work was also supported by the French-Polish PHC Polonium 34852WG grant.
- 6.Flórez-Valencia, L., Morales Pinzón, A., et al.: Simultaneous skeletonization and graph description of airway trees in 3D CT images. In: Proceedings of the 25th GRETSI (2015)Google Scholar
- 8.Graham, M.W., Higgins, W.E.: Optimal graph-theoretic approach to 3D anatomical tree matching. In: Proceedings of the 3rd ISBI, pp. 109–112 (2006)Google Scholar
- 14.Mori, K., Hasegawa, J., Toriwaki, J., Anno, H., Katada, K.: Recognition of bronchus in three-dimensional X-ray CT images with applications to virtualized bronchoscopy system. In: Proceedings of the 13th International Conference on Pattern Recognition, vol. 3, pp. 528–532 (1996)Google Scholar
- 16.Polzin, T., Rühaak, J., Werner, R., Strehlow, J., Heldmann, S., et al.: Combining automatic landmark detection and variational methods for Lung CT registration. In: Proceedings of the MICCAI 5th International Workshop on Pulmonary Image Analysis, pp. 85–96 (2013)Google Scholar