Cell type discrimination based on image features of molecular component distribution.

Machine learning-based cell classifiers use cell images to automate cell-type discrimination, which is increasingly becoming beneficial in biological studies and biomedical applications. Brightfield or fluorescence images are generally employed as the classifier input variables. We propose to use Raman spectral images and a method to extract features from these spatial patterns and explore the value of this information for cell discrimination. Raman images provide information regarding distribution of chemical compounds of the considered biological entity. Since each spectral wavelength can be used to reconstruct the distribution of a given compound, spectral images provide multiple channels of information, each representing a different pattern, in contrast to brightfield and fluorescence images. Using a dataset of single living cells, we demonstrate that the spatial information can be ranked by a Fisher discriminant score, and that the top-ranked features can accurately classify cell types. This method is compared with the conventional Raman spectral analysis. We also propose to combine the information from whole spectral analyses and selected spatial features and show that this yields higher classification accuracy. This method provides the basis for a novel and systematic analysis of cell-type investigation using Raman spectral imaging, which may benefit several studies and biomedical applications.