Segmentation of tongue muscles from super-resolution magnetic resonance images

Bulat Ibragimov; Jerry L Prince; Emi Z Murano; Jonghye Woo; Maureen Stone; Boštjan Likar; Franjo Pernuš; Tomaž Vrtovec

doi:10.1016/j.media.2014.11.006

Segmentation of tongue muscles from super-resolution magnetic resonance images

Med Image Anal. 2015 Feb;20(1):198-207. doi: 10.1016/j.media.2014.11.006. Epub 2014 Nov 23.

Authors

Bulat Ibragimov¹, Jerry L Prince², Emi Z Murano³, Jonghye Woo⁴, Maureen Stone⁵, Boštjan Likar⁶, Franjo Pernuš⁶, Tomaž Vrtovec⁶

Affiliations

¹ Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia; Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA. Electronic address: bulat.ibragimov@fe.uni-lj.si.
² Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA.
³ Department of Otolaryngology, Head and Neck Surgery, Johns Hopkins University, Baltimore, MD, USA.
⁴ Department of Radiology, Harvard Medical School/MGH, Boston, MA, USA.
⁵ Department of Oral and Craniofacial Biological Sciences, University of Maryland, Baltimore, MD, USA; Department of Orthodontics, University of Maryland, Baltimore, MD, USA.
⁶ Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia.

Abstract

Imaging and quantification of tongue anatomy is helpful in surgical planning, post-operative rehabilitation of tongue cancer patients, and studying of how humans adapt and learn new strategies for breathing, swallowing and speaking to compensate for changes in function caused by disease, medical interventions or aging. In vivo acquisition of high-resolution three-dimensional (3D) magnetic resonance (MR) images with clearly visible tongue muscles is currently not feasible because of breathing and involuntary swallowing motions that occur over lengthy imaging times. However, recent advances in image reconstruction now allow the generation of super-resolution 3D MR images from sets of orthogonal images, acquired at a high in-plane resolution and combined using super-resolution techniques. This paper presents, to the best of our knowledge, the first attempt towards automatic tongue muscle segmentation from MR images. We devised a database of ten super-resolution 3D MR images, in which the genioglossus and inferior longitudinalis tongue muscles were manually segmented and annotated with landmarks. We demonstrate the feasibility of segmenting the muscles of interest automatically by applying the landmark-based game-theoretic framework (GTF), where a landmark detector based on Haar-like features and an optimal assignment-based shape representation were integrated. The obtained segmentation results were validated against an independent manual segmentation performed by a second observer, as well as against B-splines and demons atlasing approaches. The segmentation performance resulted in mean Dice coefficients of 85.3%, 81.8%, 78.8% and 75.8% for the second observer, GTF, B-splines atlasing and demons atlasing, respectively. The obtained level of segmentation accuracy indicates that computerized tongue muscle segmentation may be used in surgical planning and treatment outcome analysis of tongue cancer patients, and in studies of normal subjects and subjects with speech and swallowing problems.

Keywords: Atlasing; Game theory; Human tongue; Magnetic resonance imaging; Segmentation.

Publication types

Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

MeSH terms

Databases, Factual
Game Theory
Humans
Magnetic Resonance Imaging / methods*
Muscles / anatomy & histology
Tongue / anatomy & histology*

Abstract

Publication types

MeSH terms

Grants and funding