Analysis of Performance Metrics with Mesenchymal Stem Cell Classification and Optimization Algorithms

Abstract

Stem cells are biological cells found in all multicellular organisms, that can divide (through mitosis) and differentiate into diverse specialized cell types and can self-renew to produce more stem cells. Optimization algorithms have been proved to be good solutions for many practical applications. They were mainly inspired by natural evolutions. However, they are still faced to some problems such as trapping in local minimums, having low speed of convergence, and also having high order of complexity for implementation. Mesenchymal Stems or stromal Cells (MSCs) are part of maintaining as well as repairing tissues. The functions are mainly examined in bone marrow-derived MSC. In the current study, segmentations are performed through usage of Graph-based image segmentations. Feature extraction is performed through Wavelet while Feature Selection is performed through Stem Cell Optimization techniques. Naïve Bayes as well as Support Vector Machines are utilized for classifiers. Results show that the Stem Cell Optimization has better classification accuracy than Information Gain (IG) and Genetic Algorithm (GA).