Title :
Improved endoscope distortion correction does not necessarily enhance mucosa-classification based medical decision support systems
Author :
Gschwandtner, M. ; Hämmerle-Uhl, J. ; Höller, Y. ; Liedlgruber, M. ; Uhl, A. ; Vecsei, A.
Author_Institution :
Dept. of Comput. Sci., Univ. of Salzburg, Salzburg, Austria
Abstract :
Distortion correction in two variants is applied to endoscopic duodenal imagery aiming at an improvement of automated classification of celiac disease affected mucosa patches. In a set of heterogeneous feature extraction techniques, only geometry and shape related ones are able to benefit from distortion correction, while for others, even a decrease of classification accuracy is observed. Different types of distortion correction do not lead to significantly different behaviour in the observed application scenario.
Keywords :
decision support systems; diseases; endoscopes; image classification; medical computing; patient diagnosis; automated classification; celiac disease; endoscope distortion correction; endoscopic duodenal imagery; heterogeneous feature extraction techniques; medical decision support systems; mucosa patches; mucosa-classification; Accuracy; Calibration; Diseases; Endoscopes; Feature extraction; Image edge detection; Nonlinear distortion; endoscope distortion correction; medical decision support systems; mucosa texture classification;
Conference_Titel :
Multimedia Signal Processing (MMSP), 2012 IEEE 14th International Workshop on
Conference_Location :
Banff, AB
Print_ISBN :
978-1-4673-4570-5
Electronic_ISBN :
978-1-4673-4571-2
DOI :
10.1109/MMSP.2012.6343433
