Progress in Industrial Mathematics at ECMI 2006 pp 538-542 | Cite as
Size Functions Applied to the Statistical Shape Analysis and Classification of Tumor Cells
Conference paper
Here the Theory of Size Functions is introduced and joined to some statistical techniques of discriminant analysis, to perform automatic classification of families of random shapes. The method is applied to the classification of normal and malignant tumor cell nuclei, described via their section profiles. The results here reported are compared with other techniques of shape analysis, already applied to the same data, showing some improvements.
Preview
Unable to display preview. Download preview PDF.
References
- 1.M. D'Amico, P. Frosini, C. Landi, Natural pseudo-distance and optimal matching between reduced size functions, Preprint, 2005.Google Scholar
- 2.I. L. Dryden, K. V. Mardia, Statistical Shape Analysis, Wiley, New York, 1998.MATHGoogle Scholar
- 3.P. Frosini, C. Landi, Size theory as a topological tool for computer vision, Pattern Recognition and Image Analysis 9, pp. 596-603, 1999.Google Scholar
- 4.P. Frosini, C. Landi, Size functions and formal series, AAECC 12, pp. 327-349, 2001.MATHCrossRefMathSciNetGoogle Scholar
- 5.P. Frosini, M. Pittore, New methods for reducing size graphs, Intern. J. Computer Math. 70, pp. 505-517, 1999.MATHCrossRefMathSciNetGoogle Scholar
- 6.P.A. Lachenbruch, Discriminant Analysis, Hafner Press, New York, 1975.MATHGoogle Scholar
- 7.G. Landini, J.W. Rippin, Quantification of nuclear pleomorphism using an asymptotic fractal model, Anal. Quant. Cyt. Hist., 18, pp. 167-176, 1996.Google Scholar
- 8.A. Micheletti, Statistical shape analysis applied to automatic recognition of tumor cells, Fractals in Biology and Medicine IV, G.A. Losa et al. Editors, Birkhauser Verlag, Basel, pp. 165-174, 2005.CrossRefGoogle Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2008