2D-PAGE Analysis Using Evolutionary Computation

2D-PAGE Analysis Using Evolutionary Computation

Pablo Mesejo (University of A Coroña, Spain), Enrique Fernández-Blanco (University of A Coroña, Spain), Diego Martínez-Feijóo (University of A Coroña, Spain) and Francisco J. Blanco (Juan Canalejo Hospital, Spain)
Copyright: © 2009 |Pages: 6
DOI: 10.4018/978-1-59904-849-9.ch232
OnDemand PDF Download:
$37.50

Abstract

This paper presents the preliminary studies for the creation of a new tool to assist in medical diagnostic. The tool will help in the analysis of 2D-PAGE images. In order to create a 2D-PAGE image of an ideal patient—the patient could be healthy or ill—the tool will help us in the creation of an image that facilitates and speeds up future diagnostics. The creation of a master image has motivated the development of a tool to alignment gel images. The tool will make easier the correspondence among the proteins into the ideal image and the ones of a new image. Due to the fact that image registering process is quite complex, we use the Intel’s library OpenCV which provides functions to calculate optical flow and translation vectors. This library introduces into the project a set of variables unknown by the facultative. To solve this, an automatic selection of values for this set of variables is necessary. This last task is made with the Evolutionary Computation technique called Particle Swarm Optimization (Kennedy, R. & Eberhart, J. 1995)
Chapter Preview
Top

Background

In the 20th century medicine, the number of medical images has been growing. X-ray photographies, magnetic resonances, 2D gels images, angiographies can be taken as examples. The major difficulty for the physician is to integrate all this information in order to offer a diagnosis.

This way, since computers started being used for analyzing and treating images at the end of the 20th century, one of the most important fields inside the application of computers to image processing has been the treatment of all medical existing images. It is here where technologies of Evolutionary Computation and Neural Networks are necessary, because they facilitate certain processes of adjustment that, in another way, would be extraordinarily complex or laborious. Among the most usual technologies used for the processing of biomedical images there can be pointed out Artificial Neural Networks, Genetic Algorithms, Particle Swarm Optimization, Splines or Growth of Regions.

Amongst some examples, we can emphasize the use of Artificial Neural Networks for the analysis of radiological images, Genetic Algorithms (Holland, J.H.,1975) in the 3D reconstruction of anthropologic models (Santamaría, J., Cordón, O., Damas, S., Alemán, I., Botella, M., 2006) and in the integration of the information obtained by means of different methods— Computed Tomography (CT), Magnetic Resonance Imaging (MRI),…—(Rouet, J. M., Jacq. J. J., Roux, C., 2000), Particle Swarm Optimization for alignment of 2D and 3D biomedical images (Wachowiak, M. P., Smolikova, R., Zheng, Y., Zurada, J. M., Elmaghraby, A. S., 2004) or the use of Splines to 2D-PAGE registering (Seow, N., Sowmya, A., Sun, C., 2005).

In our case, the technology to use will be the Particle Swarm Optimization dedicated to improve the analysis of 2D-PAGE (Seoane, J. A., Mesejo, P., Ruiz-Romero, C., Dorado, J., Pazos, A., Blanco, F. J., 2007).

Key Terms in this Chapter

Particle: Each of the elements that explore the search space in a Particle Swarm Optimization algorithm.

Particle Swarm Optimization: Evolutionary Computation technique that basis its functioning on natural swarm behaviour like the birds. This algorithm uses a swarm of particles to explore the search space

Electrophoresis: Separation of molecules (proteins or nucleic acids) in an electric field as a function of their molecular weight and/or their electric charge.

Evolutionary Computation: Generic term used to indicate any population-based metaheuristic optimization algorithm that uses mechanisms inspired by biological evolution (Darwin, D., 1859) (Wallace, A. R., 1858), such as reproduction, mutation and recombination.

Area of the Search Space: Set of specific ranges or values of the input variables that constitute a subset of the search space.

Search Space: Set of all possible situations of the problem that we want to solve could ever be in.

Amphoteric Substance: Substance is one that can react as either an acid or base.

Genetic Algorithm: An algorithm for optimizing a property based on an evolutionary mechanism that uses replication, deletion, and mutation processes carried out over many generations. (Goldberg, D.E., 1989) (Fogel, L.J., Owens, A.J. & Walsh, M.A. 1966)

Protein: A molecule composed of a long chain of amino acids. Proteins are the principal constituents of cellular material

Artificial Neural Networks: System composed of many simple processing elements operating in parallel whose function is determined by network structure, connection strengths, and the processing performed at computing elements or nodes.

Polyacrylamide: Acrylate polymer formed from acrylamide subunits that is readily cross-linked.

Complete Chapter List

Search this Book:
Reset