Abstract
Although several algorithms for corner detection have been proposed, limited effort has been devoted to the detection of branching points, critical points of anatomic tree structures which are located inside the tree where a branch starts splitting into two thinner branches. In this paper, we propose a novel two-step approach for identifying and inferring the location of tree nodes in medical images which visualize structures of the human body of branching topology. Our methodology begins with corner detection using adaptive thresholding in order to accommodate uneven illumination across tree levels. Furthermore, a localization procedure using the k-means algorithm finds accurate locations of branching nodes. The proposed methodology is applied to a dataset of clinical X-ray galactograms and is evaluated by means of precision, recall and localization error. Despite the challenges of this kind of medical images, the experimental results demonstrate the effectiveness of the new framework compared to state-of-the-art approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Tschirren, J., McLennan, G., Palagyi, K., Hoffman, E., Sonka, M.: Matching and anatomical labeling of human airway tree. IEEE Transactions in Medical Imaging 24, 701–716 (1996)
Megalooikonomou, V., Barnathan, M., Kontos, D., Bakic, P.R., Maidment, A.D.: A Representation and Classification Scheme for Tree-like Structures in Medical Images: Analyzing the Branching Pattern of Ductal Trees in X-ray Galactograms. IEEE Transactions in Medical Imaging 28, 487–493 (2009)
Skoura, A., Barnathan, M., Megalooikonomou, V.: Classification of ductal tree structures in galactograms. In: Proc. of the 6th IEEE International Symposium on Biomedical Imaging (ISBI), pp. 1015–1018 (2009)
Azzopardi, G., Petkov, N.: Detection of retinal vascular bifurcations by trainable V4-like filters. In: Proc. of the 14th International Conference on Computer Analysis of Images and Patterns (CAIP), vol. 1, pp. 451–459 (2011)
Ling, H., Barnathan, M., Megalooikonomou, V., Bakic, P.R., Maidment, A.: Probabilistic branching node detection using local hybrid features. In: Proc. of the 6th IEEE International Symposium on Biomedical Imaging (ISBI), pp. 233–236 (2009)
Nuzhnaya, T., Barnathan, M., Ling, H., Megalooikonomou, V., Bakic, P.R., Maidment, A.D.A.: Probabilistic branching node detection using adaboost and hybrid local features. In: Proc. of the 7th IEEE International Conference on Biomedical Imaging (ISBI), pp. 221–224 (2010)
Harris, C., Stephens, M.: A Combined Corner and Edge Detector. In: Proc. of the 4th Alvey Vision Conference, pp. 147–151 (1988)
Anselin, L.: Local indicators of spatial association – LISA. Geographical Analysis 27, 93–115 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Skoura, A., Nuzhnaya, T., Bakic, P.R., Megalooikonomou, V. (2013). Detecting and Localizing Tree Nodes in Anatomic Structures of Branching Topology. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2013. Lecture Notes in Computer Science, vol 7950. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39094-4_55
Download citation
DOI: https://doi.org/10.1007/978-3-642-39094-4_55
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39093-7
Online ISBN: 978-3-642-39094-4
eBook Packages: Computer ScienceComputer Science (R0)