Medical Image Retrieval by Fuzzy Set Based Geometric Relationships

Abstract:

Modeling spatial context (e.g., autocorrelation) is a key challenge in classification and retrieval problems that arise in image processing regions. This work proposes a new approach for medical images retrieval enlightened by traditional Markov Random Field model and improve on it. Contrasting with previous work, this method relies on coping with the ambiguity of spatial relative position concepts: a new definition of the geometric relationship between two objects in a fuzzy set framework is proposed. This definition is based on a fuzzy pattern-matching approach, which comparing an object by the fuzzy set representation of the degree of position satisfaction to a reference object. Furthermore, Fuzzy Attributed Relational Graphs (FARGs) are used in this framework for the purpose of medical image similarity measurement.

• Periodical: Applied Mechanics and Materials (Volumes 44-47)
• Pages: 3154-3158
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.44-47.3154
• Online since: December 2010
• Authors: Hui Liu, Xiao Hui Xing
• Keywords: Fuzzy Attributed Relational Graph (FARG), Fuzzy Set, Geometric Relationship, Spatial Context

References

[1] LIU Hui, ZHANG Cai-ming, JI Xiu-hua and ZHANG Yun-feng, An Algorithm for Co-training in Medical Image Retrieval, International Journal of Innovative Computing, Information and Control, Vol. 5(12): 4327-4333, December (2009).

[2] L. Hollink, A. Th. Schreiber, B. Wielinga, and M. Worring. Classification of user image descriptions. Journal of Human Computer Studies, November, (2004).

DOI: 10.1016/j.ijhcs.2004.03.002

[3] S. Li. Markov random field modeling. Computer Vision. New York: Springer-Verlag, (1995).

[4] Y. Jhung, P. H. Swain. Bayesian contextural classification based on modified M-estimates and Markov Random Fields, " IEEE Trans on Pattern Anal. & Machine Intell., 34(1): 67–75, (1996).

DOI: 10.1109/36.481894

[5] I. Bloch. Fuzzy Relative Position Between Objects in Image Processing: A Morphological Approach, IEEE Trans on Pattern Anal. & Machine Intell., 21(7): 657-664, (1999).

DOI: 10.1109/34.777378

[6] R. Krishnapuram, J.M. Keller, Y. Ma. Quantitative Analysis of Properties and Spatial Relations of Fuzzy Image Regions. IEEE Trans on Fuzzy Systems, 15(3): 222–233, (1993).

DOI: 10.1109/91.236554

[7] J.M. Keller, L. Sztandera. Spatial Relations among Fuzzy Subsets of an Image. Int'l Symp. Uncertainty Modeling and Analysis, pp: 207-211, (1990).

DOI: 10.1109/isuma.1990.151251

[8] K. Miyajima, A. Ralescu. Analysis of Spatial Relations between 2D Segmented Regions. Proc. European Congress Fuzzy and Intelligent Technologies, pp: 48-54, (1993).

[9] J.M. Keller and X. Wang. Learning Spatial Relationships in Computer Vision. Int'l Conf. Fuzzy Systems, pp: 118-124, (1996).

[10] P. Matsakis, L. Wendling, J. Desachy. A New Way to Represent Relative Position between Areal Objects. IEEE Trans on Pattern Anal. & Machine Intell., 21(7): 634-643, (1999).

DOI: 10.1109/34.777374

[11] K.P. Chan and Y.S. Cheung. Fuzzy-Attribute Graph with Application to Chinese Character Recognition. IEEE Trans on Systems, Man, and Cybernetics, 22(1): 153-160, (1992).

DOI: 10.1109/21.141319

[12] T.M. Lehmann, M.O. Güld, C. Thies, B. Plodowski, D. Keysers, B. Ott, H. Schubert, IRMA - Content-based image retrieval in medical applications, in Proc. 14th World Congress on Medical Informatics (Medinfo 2004), IOS Press, Amsterdam, vol. 2, pp.842-848, (2004).

DOI: 10.1055/s-0038-1633877