Abstract
A biomarker, or biological marker is a substance used as an indicator of a biological state. It is used in many scientific fields. The determination and function of the biomarker can be formalized more precisely by using Nonlinear Recognition Methods for accurate identification of oncological pathologies and both the pathogenic processes and pharmacologic response to a therapeutic intervention by applying dynamical systems and chaotic algorithms to determine the biological state and its dynamics. To this end a classification problem is solved based on optimal nonlinear algorithm, and it will be shown that certainty equivalent predictions are derived. Application results will be given on available test data sets of gastroscopic and colonoscopic images. The increase in the recognition accuracy is attributable to the algorithm and a strict statistical methodology without extraneous assumptions.
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.
eferences
G. Bonifazi, P. Massacci, L. Nieddu, and G. Patrizi. The classification of industrial sand-ores by image recognition methods. In Proceedings of 13th International Conference on Pattern Recognition Systems, vol.4: Parallel and Connectionist Systems, pp. 174–179, Los Alamitos, CA, 1996. IEEE Computer Society Press.
R. B. Braithwaite. Scientific Explanation: A Study of the Function of Theory, Probability, and Law in Science. Cambridge University Press, Cambridge, 1953.
C. Cifarelli and G. Patrizi. Solving large protein secondary structure classification problems by a nonlinear complementarity algorithm with 0, 1 variables. Optimization Methods and Software, 22:25–49, 2007.
L. Devroye, L. Gyorfi, and G. Lugosi. A Probabilistic Theory of Pattern Recognition. Springer-Verlag, Berlin, 1996.
L. Di Giacomo, E. Argento, and G. Patrizi. Linear complementarity methods for the solution of combinatorial problems. Informs Journal of Computing, 19:73–79, 2007.
L. Di Giacomo and G. Patrizi. Methodological analysis of supply chain management applications. European Journal of Operational Research, 207:249–257, 2010.
R. O. Duda and P. E. Hart. Pattern Recognition and Scene Analysis. Wiley, New York, 1973.
J.-S. Pang F. Facchinei. Finite-Dimensional Variational inequalities and complementarity Problems. Springer, Berlin, 2003.
H. S. Konjin. Statistical Theory of Sample Design and Analysis. North Holland, Amsterdam, 1973.
L. Nieddu and G. Patrizi. Formal properties of pattern recognition algorithms: A review. European Journal of Operational Research, 120:459–495, 2000.
G. Patrizi. Optimal clustering properties. Ricerca Operativa, 10:41–64, 1979.
G. Patrizi. The equivalence of an lcp to a parametric linear program with a scalar paramter. European Journal of Operational Research, 51:367–386, 1991.
Giacomo Patrizi, L. Nieddu, P. Mingazzini, F. Paparo, Gregorio Patrizi, C. Provenza, F. Ricci, and L. Memeo. Algoritmi di supporto alla diagnosi istopatologica delle neoplasie del colon. In C. Davino and N. C. Lauro, editors, Data Mining e Analisi Simbolica, pp. 205–223. Franco Angeli, Milano, 2004.
Gregorio Patrizi, C. Cifarelli, V. Losacco, and Giacomo Patrizi. Secondary structure classification of isoform protein markers in oncology. In R. Bruni, editor, Mathematical Approaches to Polymer Sequence Analysis and Related Problems, pp. 47–67. Springer, New York, 2011.
P. Rubiczey, A. Tordai, H. Andrikovics amd A. G. Filoteo, J. T. Penniston, J. Enouf, A. Enyedi, B. Papp, and T. Kovacs. Isoform-specific up-regulation of plasma membrane Ca2 + ATPase expression during colon and gastric cancer cell differentiation. Cell Calcium, 42:590–605, 2007.
A. Stangelberger, M. Margreiter, C. Seitz, and B. Djavan. Prostate cancer screening makers. The Journal of Men’s Health & Gender, 4:233–244, 2007.
I. E. Tothill. Biosensors for cancer markers diagnosis. Seminars in Cell and Development Biology, 20:55–62, 2009.
V. N. Vapnik. Learning Theory. Wiley, New York, 1998.
R. Wolf, C. Vascopoulos, J. Winston, A. Dharamsi, P. Goldsmith, M. Gunsior, B. K. Vonderhaar, M. Olson, and P. H. Watson. Highly homologous hs100a15 and hs100a7 proteins are distinctly expressed in normal breast tissue and breast cancer. Cancer Letters, 277:101–107, 2009.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Patrizi, G. et al. (2012). Nonlinear Recognition Methods for Oncological Pathologies. In: Pardalos, P., Xanthopoulos, P., Zervakis, M. (eds) Data Mining for Biomarker Discovery. Springer Optimization and Its Applications(), vol 65. Springer, Boston, MA. https://doi.org/10.1007/978-1-4614-2107-8_9
Download citation
DOI: https://doi.org/10.1007/978-1-4614-2107-8_9
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4614-2106-1
Online ISBN: 978-1-4614-2107-8
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)