Improved endoscope distortion correction does not necessarily enhance mucosa-classification based medical decision support systems

M. Gschwandtner*, J. Hammerle-Uhl, Yvonne Höller, M. Liedlgruber, A. Uhl, A. Vecsei

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Citations (Scopus)

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.

Original languageEnglish
Title of host publication2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012 - Proceedings
Pages158-163
Number of pages6
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012 - Banff, AB, Canada
Duration: 17 Sept 201219 Sept 2012

Publication series

Name2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012 - Proceedings

Conference

Conference2012 IEEE 14th International Workshop on Multimedia Signal Processing, MMSP 2012
Country/TerritoryCanada
CityBanff, AB
Period17/09/1219/09/12

Other keywords

  • endoscope distortion correction
  • medical decision support systems
  • mucosa texture classification

Fingerprint

Dive into the research topics of 'Improved endoscope distortion correction does not necessarily enhance mucosa-classification based medical decision support systems'. Together they form a unique fingerprint.

Cite this