Texture analysis of fluorescence microscopic images of colonic tissue sections

The aim of this study was to assess the potential of texture analysis for t he characterization of fluorescence images from colonic tissue sections sta ined with a novel and selective fluoroprobe, Rhodamine B-phenylboronic acid , Fluorescence microscopy images of colonic healthy mucosa (n=35) and adeno carcinomas (n=35) were digitally captured and subjected to image texture an alysis. Textural features derived from the grey level co-occurrence matrix were calculated. A modified version of the multiple discriminant analysis c riterion was used to choose an appropriate subset of features. A minimum Ma halanobis distance, linear discriminant classifier and a simple evaluation 'score' method were used to classify image feature data into the two catego ries. A subset of four textural features was selected and used for the desc ription and classification of each image field. They were found appropriate to correctly classify 95% of the images into the two classes, using two di fferent classifiers. These features contained information about local homog eneity and grey level linear dependencies of the image. This study demonstr ated that texture analysis techniques could provide valuable diagnostic dec ision support in a complex domain such as colorectal tissue.