Towards automated diagnosis of celiac disease by computer-assisted classification of duodenal imagery

Various techniques have been developed for texture classification which can be used for an automated classification of endoscopic images. A certain subset of these techniques is applied to duodenal imagery for diagnosis of celiac disease. Spatial domain (histogram) and transform domain (wavelet) features are extracted from the images for subsequent classification with various algorithms (KNN, SVM, Bayes classifier). The obtained results are promising, due to a high specificity for the detection of mucosal damage typical of untreated celiac disease.