Semi-automatic segmentation of tongue tumors from magnetic resonance imaging

Trushali Doshi, John Soraghan, Lykourgos Petropoulakis, Derek Gross, Kenneth MacKenzie

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

4 Citations (Scopus)

Abstract

Radiation therapy is one of the most effective modalities for treatment of tongue cancer. In order to optimize radiation dose to the tumor region, it is necessary to segment the tumor from normal region. This paper presents a new semiautomatic algorithm that is demonstrated to be able to segment tongue tumor from gadolinium-enhanced T1-weighted magnetic resonance imaging (MRI) to support radiation planning. This algorithm takes sequential MRI slices with visible tongue tumor. The Tumor's region from each slice is segmented using three steps (i) preprocessing, (ii) initialization and (iii) localized region-based level set segmentation. The segmentation results obtained from proposed algorithm are compared with manual segmentation from clinical expert. Results from 9 MRI slices show that there is a good overlap between semi-automatic and manual segmentation results with dice similarity coefficient (DSC) of 0.87±0.05.
Original languageEnglish
Title of host publication2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP)
PublisherIEEE
Pages143-146
Number of pages4
ISBN (Print)9781479909414
DOIs
Publication statusPublished - 9 Nov 2013
Event2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP) - Bucharest, Romania
Duration: 7 Jul 20139 Jul 2013

Conference

Conference2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP)
CountryRomania
CityBucharest
Period7/07/139/07/13

Keywords

  • biomedical MRI
  • cancer
  • image segmentation
  • image sequences
  • medical image processing
  • radiation therapy
  • set theory
  • tumours
  • head
  • tongue
  • magnetic resonance imaging

Fingerprint Dive into the research topics of 'Semi-automatic segmentation of tongue tumors from magnetic resonance imaging'. Together they form a unique fingerprint.

  • Cite this

    Doshi, T., Soraghan, J., Petropoulakis, L., Gross, D., & MacKenzie, K. (2013). Semi-automatic segmentation of tongue tumors from magnetic resonance imaging. In 2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP) (pp. 143-146). IEEE. https://doi.org/10.1109/IWSSIP.2013.6623474