Semi-automatic segmentation of the tongue for 3D motion analysis with dynamic MRI

Junghoon Lee, Jonghye Woo, Fangxu Xing, Emi Z. Murano, Maureen Stone, Jerry Ladd Prince

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

Abstract

Accurate segmentation is an important preprocessing step for measuring the internal deformation of the tongue during speech and swallowing using 3D dynamic MRI. In an MRI stack, manual segmentation of every 2D slice and time frame is time-consuming due to the large number of volumes captured over the entire task cycle. In this paper, we propose a semi-automatic segmentation workflow for processing 3D dynamic MRI of the tongue. The steps comprise seeding a few slices, seed propagation by deformable registration, random walker segmentation of the temporal stack of images and 3D super-resolution volumes. This method was validated on the tongue of two subjects carrying out the same speech task with multi-slice 2D dynamic cine-MR images obtained at three orthogonal orientations and 26 time frames. The resulting semi-automatic segmentations of 52 volumes showed an average dice similarity coefficient (DSC) score of 0.9 with reduced segmented volume variability compared to manual segmentations.

Original languageEnglish (US)
Title of host publicationProceedings - International Symposium on Biomedical Imaging
Pages1465-1468
Number of pages4
DOIs
StatePublished - 2013
Event2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013 - San Francisco, CA, United States
Duration: Apr 7 2013Apr 11 2013

Other

Other2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013
CountryUnited States
CitySan Francisco, CA
Period4/7/134/11/13

Fingerprint

Tongue
Magnetic resonance imaging
Seed
Workflow
Deglutition
Seeds
Processing
Motion analysis

Keywords

  • deformable registration
  • random walker
  • segmentation
  • super-resolution reconstruction
  • Tongue

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Lee, J., Woo, J., Xing, F., Murano, E. Z., Stone, M., & Prince, J. L. (2013). Semi-automatic segmentation of the tongue for 3D motion analysis with dynamic MRI. In Proceedings - International Symposium on Biomedical Imaging (pp. 1465-1468). [6556811] https://doi.org/10.1109/ISBI.2013.6556811

Semi-automatic segmentation of the tongue for 3D motion analysis with dynamic MRI. / Lee, Junghoon; Woo, Jonghye; Xing, Fangxu; Murano, Emi Z.; Stone, Maureen; Prince, Jerry Ladd.

Proceedings - International Symposium on Biomedical Imaging. 2013. p. 1465-1468 6556811.

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

Lee, J, Woo, J, Xing, F, Murano, EZ, Stone, M & Prince, JL 2013, Semi-automatic segmentation of the tongue for 3D motion analysis with dynamic MRI. in Proceedings - International Symposium on Biomedical Imaging., 6556811, pp. 1465-1468, 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013, San Francisco, CA, United States, 4/7/13. https://doi.org/10.1109/ISBI.2013.6556811
Lee J, Woo J, Xing F, Murano EZ, Stone M, Prince JL. Semi-automatic segmentation of the tongue for 3D motion analysis with dynamic MRI. In Proceedings - International Symposium on Biomedical Imaging. 2013. p. 1465-1468. 6556811 https://doi.org/10.1109/ISBI.2013.6556811
Lee, Junghoon ; Woo, Jonghye ; Xing, Fangxu ; Murano, Emi Z. ; Stone, Maureen ; Prince, Jerry Ladd. / Semi-automatic segmentation of the tongue for 3D motion analysis with dynamic MRI. Proceedings - International Symposium on Biomedical Imaging. 2013. pp. 1465-1468
@inproceedings{8e90cf6f3655469395681ba5bcc99c97,
title = "Semi-automatic segmentation of the tongue for 3D motion analysis with dynamic MRI",
abstract = "Accurate segmentation is an important preprocessing step for measuring the internal deformation of the tongue during speech and swallowing using 3D dynamic MRI. In an MRI stack, manual segmentation of every 2D slice and time frame is time-consuming due to the large number of volumes captured over the entire task cycle. In this paper, we propose a semi-automatic segmentation workflow for processing 3D dynamic MRI of the tongue. The steps comprise seeding a few slices, seed propagation by deformable registration, random walker segmentation of the temporal stack of images and 3D super-resolution volumes. This method was validated on the tongue of two subjects carrying out the same speech task with multi-slice 2D dynamic cine-MR images obtained at three orthogonal orientations and 26 time frames. The resulting semi-automatic segmentations of 52 volumes showed an average dice similarity coefficient (DSC) score of 0.9 with reduced segmented volume variability compared to manual segmentations.",
keywords = "deformable registration, random walker, segmentation, super-resolution reconstruction, Tongue",
author = "Junghoon Lee and Jonghye Woo and Fangxu Xing and Murano, {Emi Z.} and Maureen Stone and Prince, {Jerry Ladd}",
year = "2013",
doi = "10.1109/ISBI.2013.6556811",
language = "English (US)",
isbn = "9781467364546",
pages = "1465--1468",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Semi-automatic segmentation of the tongue for 3D motion analysis with dynamic MRI

AU - Lee, Junghoon

AU - Woo, Jonghye

AU - Xing, Fangxu

AU - Murano, Emi Z.

AU - Stone, Maureen

AU - Prince, Jerry Ladd

PY - 2013

Y1 - 2013

N2 - Accurate segmentation is an important preprocessing step for measuring the internal deformation of the tongue during speech and swallowing using 3D dynamic MRI. In an MRI stack, manual segmentation of every 2D slice and time frame is time-consuming due to the large number of volumes captured over the entire task cycle. In this paper, we propose a semi-automatic segmentation workflow for processing 3D dynamic MRI of the tongue. The steps comprise seeding a few slices, seed propagation by deformable registration, random walker segmentation of the temporal stack of images and 3D super-resolution volumes. This method was validated on the tongue of two subjects carrying out the same speech task with multi-slice 2D dynamic cine-MR images obtained at three orthogonal orientations and 26 time frames. The resulting semi-automatic segmentations of 52 volumes showed an average dice similarity coefficient (DSC) score of 0.9 with reduced segmented volume variability compared to manual segmentations.

AB - Accurate segmentation is an important preprocessing step for measuring the internal deformation of the tongue during speech and swallowing using 3D dynamic MRI. In an MRI stack, manual segmentation of every 2D slice and time frame is time-consuming due to the large number of volumes captured over the entire task cycle. In this paper, we propose a semi-automatic segmentation workflow for processing 3D dynamic MRI of the tongue. The steps comprise seeding a few slices, seed propagation by deformable registration, random walker segmentation of the temporal stack of images and 3D super-resolution volumes. This method was validated on the tongue of two subjects carrying out the same speech task with multi-slice 2D dynamic cine-MR images obtained at three orthogonal orientations and 26 time frames. The resulting semi-automatic segmentations of 52 volumes showed an average dice similarity coefficient (DSC) score of 0.9 with reduced segmented volume variability compared to manual segmentations.

KW - deformable registration

KW - random walker

KW - segmentation

KW - super-resolution reconstruction

KW - Tongue

UR - http://www.scopus.com/inward/record.url?scp=84881641798&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881641798&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2013.6556811

DO - 10.1109/ISBI.2013.6556811

M3 - Conference contribution

C2 - 24443699

AN - SCOPUS:84881641798

SN - 9781467364546

SP - 1465

EP - 1468

BT - Proceedings - International Symposium on Biomedical Imaging

ER -