The complexities involved in the analysis of Fourier Transform Infrared Spectroscopy of breast cancer data with clustering algorithms

Abstract

Fourier Transform Infrared Spectroscopy (FTIR) is a relatively new technique that has been frequently applied now a days in cancer pathology including breast cancer. The long term aim of this work is to develop novel techniques using machine learning methods for the analysis of FTIR data sets. This paper presents the preliminary work with a case study of a FTIR data set of breast cancer with two commonly used clustering algorithms of fuzzy c-means and k-means to differentiate between different cancer grades. We also discuss the complexities involved in the analysis of spectral data sets and need to find new methods. Future work will involve efforts towards development of a novel frame work with advanced machine learning methods to extract valuable information from complex spectral data sets