Classification of Endoscopic Images Using Delaunay Triangulation-Based Edge Features

Predicting Pathology in Medical Decision Support Systems in Endoscopy of the Gastrointestinal Tract

“…Nevertheless, as already pointed out earlier, using too many images from one patient may lead to an overfitting. While we know that Tischendorf et al on average use roughly one image per patient, we are not able to get a picture about the possible degree of overfitting in case of (Häfner et al, 2010b). This is especially problematic since LOO-CV is used to assess the prediction accuracy for the system.…”

“…Features belonging to this category are for example shape-based features, describing shapes obtained by different edge-detection methods (e.g. Häfner et al (2010b)). …”

“…In order to compare two classifier-based approaches found in literature we picked two recently published approaches (found in Tischendorf et al (2010) and Häfner et al (2010b)). Some facts about these approaches are listed in Table 1 While both methods are similar in terms of the GI tract part under investigation, the pathology of interest, the prediction goal (hence, also the same number of classes), the cross-validation protocol used, and the way the ground truth has been obtained, we also notice some differences between these works.…”

“…While in (Tischendorf et al, 2010) NBI has been used, the approach presented in (Häfner et al, 2010b) is based on the application of topical staining (using color dyes), which still is common practice in clinical routine.…”

“…• Number of patients While in (Tischendorf et al, 2010) the experiments are based on images originating from 223 patients, the work presented in (Häfner et al, 2010b) makes no statements about this detail. Nevertheless, as already pointed out earlier, using too many images from one patient may lead to an overfitting.…”