Robust and fully automated segmentation of mandible from CT scans

Neslisah Torosdagli, Denise K. Liberton, Payal Verma, Murat Sincan, Janice Lee, Sumanta Pattanaik, Ulas Bagci

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

5 Citations (Scopus)

Abstract

Mandible bone segmentation from computed tomography (CT) scans is challenging due to mandible's structural irregularities, complex shape patterns, and lack of contrast in joints. Furthermore, connections of teeth to mandible and mandible to remaining parts of the skull make it extremely difficult to identify mandible boundary automatically. This study addresses these challenges by proposing a novel framework where we define the segmentation as two complementary tasks: recognition and delineation. For recognition, we use random forest regression to localize mandible in 3D. For delineation, we propose to use 3D gradient-based fuzzy connectedness (FC) image segmentation algorithm, operating on the recognized mandible sub-volume. Despite heavy CT artifacts and dental fillings, consisting half of the CT image data in our experiments, we have achieved highly accurate detection and delineation results. Specifically, detection accuracy more than 96% (measured by union of intersection (UoI)), the delineation accuracy of 91% (measured by dice similarity coefficient), and less than 1 mm in shape mismatch (Hausdorff Distance) were found.

Original languageEnglish (US)
Title of host publication2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017
PublisherIEEE Computer Society
Pages1209-1212
Number of pages4
ISBN (Electronic)9781509011711
DOIs
StatePublished - Jun 15 2017
Event14th IEEE International Symposium on Biomedical Imaging, ISBI 2017 - Melbourne, Australia
Duration: Apr 18 2017Apr 21 2017

Publication series

NameProceedings - International Symposium on Biomedical Imaging
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Other

Other14th IEEE International Symposium on Biomedical Imaging, ISBI 2017
CountryAustralia
CityMelbourne
Period4/18/174/21/17

Fingerprint

Mandible
Tomography
Dental prostheses
Image segmentation
Bone
Tooth
Skull
Artifacts
Experiments
Joints
Bone and Bones

Keywords

  • Computed Tomography
  • Craniofacial Image Analysis
  • Fuzzy Connectivity
  • Mandible Segmentation
  • Random Forest

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Torosdagli, N., Liberton, D. K., Verma, P., Sincan, M., Lee, J., Pattanaik, S., & Bagci, U. (2017). Robust and fully automated segmentation of mandible from CT scans. In 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017 (pp. 1209-1212). [7950734] (Proceedings - International Symposium on Biomedical Imaging). IEEE Computer Society. https://doi.org/10.1109/ISBI.2017.7950734

Robust and fully automated segmentation of mandible from CT scans. / Torosdagli, Neslisah; Liberton, Denise K.; Verma, Payal; Sincan, Murat; Lee, Janice; Pattanaik, Sumanta; Bagci, Ulas.

2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE Computer Society, 2017. p. 1209-1212 7950734 (Proceedings - International Symposium on Biomedical Imaging).

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

Torosdagli, N, Liberton, DK, Verma, P, Sincan, M, Lee, J, Pattanaik, S & Bagci, U 2017, Robust and fully automated segmentation of mandible from CT scans. in 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017., 7950734, Proceedings - International Symposium on Biomedical Imaging, IEEE Computer Society, pp. 1209-1212, 14th IEEE International Symposium on Biomedical Imaging, ISBI 2017, Melbourne, Australia, 4/18/17. https://doi.org/10.1109/ISBI.2017.7950734
Torosdagli N, Liberton DK, Verma P, Sincan M, Lee J, Pattanaik S et al. Robust and fully automated segmentation of mandible from CT scans. In 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE Computer Society. 2017. p. 1209-1212. 7950734. (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2017.7950734
Torosdagli, Neslisah ; Liberton, Denise K. ; Verma, Payal ; Sincan, Murat ; Lee, Janice ; Pattanaik, Sumanta ; Bagci, Ulas. / Robust and fully automated segmentation of mandible from CT scans. 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE Computer Society, 2017. pp. 1209-1212 (Proceedings - International Symposium on Biomedical Imaging).
@inproceedings{0b1b5ebf65aa4e0a89eae1b54965dad0,
title = "Robust and fully automated segmentation of mandible from CT scans",
abstract = "Mandible bone segmentation from computed tomography (CT) scans is challenging due to mandible's structural irregularities, complex shape patterns, and lack of contrast in joints. Furthermore, connections of teeth to mandible and mandible to remaining parts of the skull make it extremely difficult to identify mandible boundary automatically. This study addresses these challenges by proposing a novel framework where we define the segmentation as two complementary tasks: recognition and delineation. For recognition, we use random forest regression to localize mandible in 3D. For delineation, we propose to use 3D gradient-based fuzzy connectedness (FC) image segmentation algorithm, operating on the recognized mandible sub-volume. Despite heavy CT artifacts and dental fillings, consisting half of the CT image data in our experiments, we have achieved highly accurate detection and delineation results. Specifically, detection accuracy more than 96{\%} (measured by union of intersection (UoI)), the delineation accuracy of 91{\%} (measured by dice similarity coefficient), and less than 1 mm in shape mismatch (Hausdorff Distance) were found.",
keywords = "Computed Tomography, Craniofacial Image Analysis, Fuzzy Connectivity, Mandible Segmentation, Random Forest",
author = "Neslisah Torosdagli and Liberton, {Denise K.} and Payal Verma and Murat Sincan and Janice Lee and Sumanta Pattanaik and Ulas Bagci",
year = "2017",
month = "6",
day = "15",
doi = "10.1109/ISBI.2017.7950734",
language = "English (US)",
series = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",
pages = "1209--1212",
booktitle = "2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017",

}

TY - GEN

T1 - Robust and fully automated segmentation of mandible from CT scans

AU - Torosdagli, Neslisah

AU - Liberton, Denise K.

AU - Verma, Payal

AU - Sincan, Murat

AU - Lee, Janice

AU - Pattanaik, Sumanta

AU - Bagci, Ulas

PY - 2017/6/15

Y1 - 2017/6/15

N2 - Mandible bone segmentation from computed tomography (CT) scans is challenging due to mandible's structural irregularities, complex shape patterns, and lack of contrast in joints. Furthermore, connections of teeth to mandible and mandible to remaining parts of the skull make it extremely difficult to identify mandible boundary automatically. This study addresses these challenges by proposing a novel framework where we define the segmentation as two complementary tasks: recognition and delineation. For recognition, we use random forest regression to localize mandible in 3D. For delineation, we propose to use 3D gradient-based fuzzy connectedness (FC) image segmentation algorithm, operating on the recognized mandible sub-volume. Despite heavy CT artifacts and dental fillings, consisting half of the CT image data in our experiments, we have achieved highly accurate detection and delineation results. Specifically, detection accuracy more than 96% (measured by union of intersection (UoI)), the delineation accuracy of 91% (measured by dice similarity coefficient), and less than 1 mm in shape mismatch (Hausdorff Distance) were found.

AB - Mandible bone segmentation from computed tomography (CT) scans is challenging due to mandible's structural irregularities, complex shape patterns, and lack of contrast in joints. Furthermore, connections of teeth to mandible and mandible to remaining parts of the skull make it extremely difficult to identify mandible boundary automatically. This study addresses these challenges by proposing a novel framework where we define the segmentation as two complementary tasks: recognition and delineation. For recognition, we use random forest regression to localize mandible in 3D. For delineation, we propose to use 3D gradient-based fuzzy connectedness (FC) image segmentation algorithm, operating on the recognized mandible sub-volume. Despite heavy CT artifacts and dental fillings, consisting half of the CT image data in our experiments, we have achieved highly accurate detection and delineation results. Specifically, detection accuracy more than 96% (measured by union of intersection (UoI)), the delineation accuracy of 91% (measured by dice similarity coefficient), and less than 1 mm in shape mismatch (Hausdorff Distance) were found.

KW - Computed Tomography

KW - Craniofacial Image Analysis

KW - Fuzzy Connectivity

KW - Mandible Segmentation

KW - Random Forest

UR - http://www.scopus.com/inward/record.url?scp=85023169955&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023169955&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2017.7950734

DO - 10.1109/ISBI.2017.7950734

M3 - Conference contribution

AN - SCOPUS:85023169955

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1209

EP - 1212

BT - 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017

PB - IEEE Computer Society

ER -