Organ detection in medical images with discriminately trained deformable part model

Viktor Gál, Etienne Kerre, Domonkos Tikk

Research output: Conference contribution

4 Citations (Scopus)

Abstract

Automatic organ segmentation on a full-body scan image is a challenging task as most of the organ segmentation methods require a prior knowledge about the position of the given organ within the image. In this paper we show, how discriminately trained deformable part model can be used to acquire this prior knowledge by constructing a multi-organ detection system based on it.

Original languageEnglish
Title of host publicationICCC 2013 - IEEE 9th International Conference on Computational Cybernetics, Proceedings
Pages153-157
Number of pages5
DOIs
Publication statusPublished - nov. 7 2013
EventIEEE 9th International Conference on Computational Cybernetics, ICCC 2013 - Tihany, Hungary
Duration: júl. 8 2013júl. 10 2013

Publication series

NameICCC 2013 - IEEE 9th International Conference on Computational Cybernetics, Proceedings

Other

OtherIEEE 9th International Conference on Computational Cybernetics, ICCC 2013
CountryHungary
CityTihany
Period7/8/137/10/13

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications

Cite this

Gál, V., Kerre, E., & Tikk, D. (2013). Organ detection in medical images with discriminately trained deformable part model. In ICCC 2013 - IEEE 9th International Conference on Computational Cybernetics, Proceedings (pp. 153-157). [6617579] (ICCC 2013 - IEEE 9th International Conference on Computational Cybernetics, Proceedings). https://doi.org/10.1109/ICCCyb.2013.6617579