Supervised classification methods for mining cell differences as depicted by Raman spectroscopy

Discrimination of different cell types is very important in many medical and biological applications. Existing methodologies are based on cost inefficient technologies or tedious one-by-one empirical examination of the cells. Recently, Raman spectroscopy, a inexpensive and efficient method, has been employed for cell discrimination. Nevertheless, the traditional protocols for analyzing Raman spectra require preprocessing and peak fitting analysis which does not allow simultaneous examination of many spectra. In this paper we examine the applicability of supervised learning algorithms in the cell differentiation problem. Five different methods are presented and tested on two different datasets. Computational results show that machine learning algorithms can be employed in order to automate cell discrimination tasks. © 2011 Springer-Verlag Berlin Heidelberg.