Chemometric labeling of cereal tissues in multichannel fluorescence microscopy images using discriminant analysis

This paper presents a novel, semiautomatic method for microscopic identification of multicomponent samples, which allows the identification, location, and percentage quantity of each component to be determined. The method involves applying discriminant analysis to a sequence of multichannel fluorescence microscopy images via a supervised learning approach; by selecting groups of pixels that are representative for each component type in a "known" sample, a computer is "taught" how to recognize the behavior (i.e., fluorescence emission) of the various components when illuminated under different spectral conditions. The identity, quantity, and location of these components in "unknown" samples (i.e., samples with the same component types but in different ratios or distributions) can then be investigated. The technique therefore enables semiautomatic quantitative fluorescence microscopy and has potential as a quality control tool. This work demonstrates the application of the technique to artificial and natural samples and critically discusses its quality, potential, and limitations.