Towards automated diagnosis of celiac disease by computer-assisted classification of duodenal imagery
ABSTRACT 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.
Article: Experimental study on the impact of endoscope distortion correction on computer-assisted celiac disease diagnosis[show abstract] [hide abstract]
ABSTRACT: information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. Abstract— The impact of applying barrel distortion cor-rection to endoscopic imagery in the context of automated celiac disease diagnosis is experimentally investigated. For a large set of feature extraction techniques, it is found that contrasting to intuition, no improvement but even significant result degradation of classification accuracy can be observed. For techniques relying on geometrical properties of the image material ("shape"), moderate improvements of classification accuracy can be achieved. Reasons for this somewhat unex-pected results are discussed and ways how to exploit potential distortion correction benefits are sketched.