Automatic segmentation of bone tissue from computed tomography using a volumetric local binary patterns based method

Jukka Kaipala, Miguel Bordallo López, Simo Saarakkala, Jérôme Thevenot

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

2 Citations (Scopus)

Abstract

Segmentation of scanned tissue volumes of three-dimensional (3D) images often involves - at least partially - some manual process, as there is no standardized automatic method. A well-performing automatic segmentation would be preferable, not only because it would improve segmentation speed, but also because it would be user-independent and provide more objectivity to the task. Here we extend a 3D local binary patterns (LBP) based trabecular bone segmentation method with adaptive local thresholding and additional segmentation parameters to make it more robust yet still perform adequately when compared to traditional user-assisted segmentation. We estimate parameters for the new segmentation method (AMLM) in our experimental setting, and have two micro-computed tomography (µCT) scanned bovine trabecular bone tissue volumes segmented by both the AMLM and two experienced users. Comparison of the results shows superior performance of the AMLM.

Original languageEnglish
Title of host publicationImage Analysis - 20th Scandinavian Conference, SCIA 2017, Proceedings
EditorsPuneet Sharma, Filippo Maria Bianchi
PublisherSpringer
Pages221-232
Number of pages12
ISBN (Electronic)978-3-319-59129-2
ISBN (Print)978-3-319-59128-5
DOIs
Publication statusPublished - 1 Jun 2017
MoE publication typeA4 Article in a conference publication
Event20th Scandinavian Conference on Image Analysis, SCIA 2017 - Tromso, Norway
Duration: 12 Jun 201714 Jun 2017

Publication series

SeriesLecture Notes in Computer Science
Volume10270
ISSN0302-9743

Conference

Conference20th Scandinavian Conference on Image Analysis, SCIA 2017
CountryNorway
CityTromso
Period12/06/1714/06/17

Fingerprint

Computed Tomography
Bone
Tomography
Segmentation
Tissue
Binary
3D Image
Thresholding
Three-dimensional
Estimate

Keywords

  • 3D
  • LBP
  • Micro-CT
  • Segmentation

Cite this

Kaipala, J., López, M. B., Saarakkala, S., & Thevenot, J. (2017). Automatic segmentation of bone tissue from computed tomography using a volumetric local binary patterns based method. In P. Sharma, & F. M. Bianchi (Eds.), Image Analysis - 20th Scandinavian Conference, SCIA 2017, Proceedings (pp. 221-232). Springer. Lecture Notes in Computer Science, Vol.. 10270 https://doi.org/10.1007/978-3-319-59129-2_19
Kaipala, Jukka ; López, Miguel Bordallo ; Saarakkala, Simo ; Thevenot, Jérôme. / Automatic segmentation of bone tissue from computed tomography using a volumetric local binary patterns based method. Image Analysis - 20th Scandinavian Conference, SCIA 2017, Proceedings. editor / Puneet Sharma ; Filippo Maria Bianchi. Springer, 2017. pp. 221-232 (Lecture Notes in Computer Science, Vol. 10270).
@inproceedings{6b18c2cb5eb9450b83d441542a9a075f,
title = "Automatic segmentation of bone tissue from computed tomography using a volumetric local binary patterns based method",
abstract = "Segmentation of scanned tissue volumes of three-dimensional (3D) images often involves - at least partially - some manual process, as there is no standardized automatic method. A well-performing automatic segmentation would be preferable, not only because it would improve segmentation speed, but also because it would be user-independent and provide more objectivity to the task. Here we extend a 3D local binary patterns (LBP) based trabecular bone segmentation method with adaptive local thresholding and additional segmentation parameters to make it more robust yet still perform adequately when compared to traditional user-assisted segmentation. We estimate parameters for the new segmentation method (AMLM) in our experimental setting, and have two micro-computed tomography (µCT) scanned bovine trabecular bone tissue volumes segmented by both the AMLM and two experienced users. Comparison of the results shows superior performance of the AMLM.",
keywords = "3D, LBP, Micro-CT, Segmentation",
author = "Jukka Kaipala and L{\'o}pez, {Miguel Bordallo} and Simo Saarakkala and J{\'e}r{\^o}me Thevenot",
year = "2017",
month = "6",
day = "1",
doi = "10.1007/978-3-319-59129-2_19",
language = "English",
isbn = "978-3-319-59128-5",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "221--232",
editor = "Puneet Sharma and Bianchi, {Filippo Maria}",
booktitle = "Image Analysis - 20th Scandinavian Conference, SCIA 2017, Proceedings",
address = "Germany",

}

Kaipala, J, López, MB, Saarakkala, S & Thevenot, J 2017, Automatic segmentation of bone tissue from computed tomography using a volumetric local binary patterns based method. in P Sharma & FM Bianchi (eds), Image Analysis - 20th Scandinavian Conference, SCIA 2017, Proceedings. Springer, Lecture Notes in Computer Science, vol. 10270, pp. 221-232, 20th Scandinavian Conference on Image Analysis, SCIA 2017, Tromso, Norway, 12/06/17. https://doi.org/10.1007/978-3-319-59129-2_19

Automatic segmentation of bone tissue from computed tomography using a volumetric local binary patterns based method. / Kaipala, Jukka; López, Miguel Bordallo; Saarakkala, Simo; Thevenot, Jérôme.

Image Analysis - 20th Scandinavian Conference, SCIA 2017, Proceedings. ed. / Puneet Sharma; Filippo Maria Bianchi. Springer, 2017. p. 221-232 (Lecture Notes in Computer Science, Vol. 10270).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Automatic segmentation of bone tissue from computed tomography using a volumetric local binary patterns based method

AU - Kaipala, Jukka

AU - López, Miguel Bordallo

AU - Saarakkala, Simo

AU - Thevenot, Jérôme

PY - 2017/6/1

Y1 - 2017/6/1

N2 - Segmentation of scanned tissue volumes of three-dimensional (3D) images often involves - at least partially - some manual process, as there is no standardized automatic method. A well-performing automatic segmentation would be preferable, not only because it would improve segmentation speed, but also because it would be user-independent and provide more objectivity to the task. Here we extend a 3D local binary patterns (LBP) based trabecular bone segmentation method with adaptive local thresholding and additional segmentation parameters to make it more robust yet still perform adequately when compared to traditional user-assisted segmentation. We estimate parameters for the new segmentation method (AMLM) in our experimental setting, and have two micro-computed tomography (µCT) scanned bovine trabecular bone tissue volumes segmented by both the AMLM and two experienced users. Comparison of the results shows superior performance of the AMLM.

AB - Segmentation of scanned tissue volumes of three-dimensional (3D) images often involves - at least partially - some manual process, as there is no standardized automatic method. A well-performing automatic segmentation would be preferable, not only because it would improve segmentation speed, but also because it would be user-independent and provide more objectivity to the task. Here we extend a 3D local binary patterns (LBP) based trabecular bone segmentation method with adaptive local thresholding and additional segmentation parameters to make it more robust yet still perform adequately when compared to traditional user-assisted segmentation. We estimate parameters for the new segmentation method (AMLM) in our experimental setting, and have two micro-computed tomography (µCT) scanned bovine trabecular bone tissue volumes segmented by both the AMLM and two experienced users. Comparison of the results shows superior performance of the AMLM.

KW - 3D

KW - LBP

KW - Micro-CT

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85020480785&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-59129-2_19

DO - 10.1007/978-3-319-59129-2_19

M3 - Conference article in proceedings

AN - SCOPUS:85020480785

SN - 978-3-319-59128-5

T3 - Lecture Notes in Computer Science

SP - 221

EP - 232

BT - Image Analysis - 20th Scandinavian Conference, SCIA 2017, Proceedings

A2 - Sharma, Puneet

A2 - Bianchi, Filippo Maria

PB - Springer

ER -

Kaipala J, López MB, Saarakkala S, Thevenot J. Automatic segmentation of bone tissue from computed tomography using a volumetric local binary patterns based method. In Sharma P, Bianchi FM, editors, Image Analysis - 20th Scandinavian Conference, SCIA 2017, Proceedings. Springer. 2017. p. 221-232. (Lecture Notes in Computer Science, Vol. 10270). https://doi.org/10.1007/978-3-319-59129-2_19