A hybrid feature selection strategy for image defining features: towards interpretation of optic nerve images

Modern imaging techniques such as confocal scanning laser tomography (CSLT) capture high-quality optic nerve images. The automated analysis of CSLT images, by combining image processing and data mining methods, offers the potential for developing objective methods for supporting clinical decision-making in glaucoma. We present our approach that involves the analysis of CSLT images using moment methods to derive abstract image defining features, and then the use of these features to train classifiers for automatically distinguishing CSLT images of healthy and diseased optic nerves. As a first step, in this paper, we present investigations in feature subset selection methods for reducing the relatively large input space produced by the moment methods. Our results demonstrate that our methods can discriminate between healthy and glaucomatous optic nerves based on shape information automatically derived from CSLT tomography images.