Abstract
Curvilinear structures are useful features, particularly in medical image analysis. Typically, a pixel-wise comparison with manually specified ground truth is used for performance evaluation. In this paper we propose a novel structure-based methodology for evaluating the performance of curvilinear structure detection algorithms. We consider the two aspects of performance, namely detection rate and detection accuracy, separately. This is in contrast to their mixed handling in earlier approaches that typically produces biased impression of detection quality. The proposed performance measures provide a more informative and precise performance characterization. A series of experiments in the context of retinal vessel detection are presented to demonstrate the advantages of our approach.
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
Cardoner, R., Thomas, F.: Residuals + directional gaps = skeletons. Pattern Recognition Letters 18(4), 343–353 (1997)
Gabow, H., Tarjan, R.: Faster scaling algorithms for network problems. SIAM Journal on Computing 18(5), 1013–1036 (1989)
Goldberg, A., Kennedy, R.: An efficient cost scaling Algorithm for the assignment problem. Math. Prog. 71, 153–178 (1995)
Hoover, A., et al.: Locating blood vessels in retinal images by piece-wise threshold probing of a matched filter response. IEEE Trans. on Medical Imaging 19(3), 203–210 (2000)
Jiang, X., Mojon, D.: Supervised evaluation methodology for curvilinear structure detection algorithms. In: Proc. of 16th Int. Conf. on Pattern Recognition, vol. I, pp. 103–106 (2002)
Jiang, X., Mojon, D.: Adaptive local thresholding by verification-based multi-threshold probing with application to vessel detection in retinal images. IEEE Trans. on PAMI 25(1), 131–137 (2003)
Lam, B.S.Y.: General retinal vessel segmentation using regularization-based multiconcavity modeling. IEEE Trans. Med. Imaging 29(7), 1369–1381 (2010)
Maurer, C.R., et al.: Exact Euclidean distance transforms of binary images in arbitrary dimensions. IEEE Trans. on PAMI 25(2), 265–270 (2003)
Niemeijer, M., et al.: Comparative study of retinal vessel segmentation methods on a new publicly available database. In: Fitzpatrick, J., Sonka, M. (eds.) SPIE Medical Imaging, vol. 5370, pp. 648–656 (2004)
Staal, J., et al.: Ridge-based vessel segmentation in color images of the retina. IEEE Trans. on Medical Imaging 23(4), 501–509 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jiang, X., Lambers, M., Bunke, H. (2011). Structure-Based Evaluation Methodology for Curvilinear Structure Detection Algorithms. In: Jiang, X., Ferrer, M., Torsello, A. (eds) Graph-Based Representations in Pattern Recognition. GbRPR 2011. Lecture Notes in Computer Science, vol 6658. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-20844-7_31
Download citation
DOI: https://doi.org/10.1007/978-3-642-20844-7_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-20843-0
Online ISBN: 978-3-642-20844-7
eBook Packages: Computer ScienceComputer Science (R0)