Automated vertebrae extraction using watershed segmentation and tree-based modelling approach

Ili Ayuni Mohd Ikhsan, Aini Hussain, Mohd Asyraf Zulkifley, Aouache Mustapha

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Vertebra segmentation and extraction are essential steps for automated vertebrae fracture assessment system. This study focuses on vertebra segmentation, which is a challenging task due to high noise and poor contrast of X-Ray images. The objective of this study is to develop and test an automated cervical vertebrae extraction to facilitate the medical researchers and physicians. The novelty of the proposed method is the combination of watershed segmentation and tree-based modelling algorithm. The proposed method has been successfully applied to a set of 50 cervical X-Ray images. Five performance metrics are calculated, which are accuracy, sensitivity, specificity, correlation and error where the best obtained results are 0.9886, 0.0655, 0.99, 0.7246 and 0.01135, respectively.

Original languageEnglish
Pages (from-to)547-555
Number of pages9
JournalJournal of Fiber Bioengineering and Informatics
Volume8
Issue number3
DOIs
Publication statusPublished - 1 Sep 2015

Fingerprint

Watersheds
X rays

Keywords

  • Cervical Vertebrae
  • Medical Imaging
  • Segmentation
  • Tree-based Modelling
  • Watershed

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)

Cite this

Automated vertebrae extraction using watershed segmentation and tree-based modelling approach. / Ikhsan, Ili Ayuni Mohd; Hussain, Aini; Zulkifley, Mohd Asyraf; Mustapha, Aouache.

In: Journal of Fiber Bioengineering and Informatics, Vol. 8, No. 3, 01.09.2015, p. 547-555.

Research output: Contribution to journalArticle

@article{487290c8de1646c1b4715d3bbe673f5c,
title = "Automated vertebrae extraction using watershed segmentation and tree-based modelling approach",
abstract = "Vertebra segmentation and extraction are essential steps for automated vertebrae fracture assessment system. This study focuses on vertebra segmentation, which is a challenging task due to high noise and poor contrast of X-Ray images. The objective of this study is to develop and test an automated cervical vertebrae extraction to facilitate the medical researchers and physicians. The novelty of the proposed method is the combination of watershed segmentation and tree-based modelling algorithm. The proposed method has been successfully applied to a set of 50 cervical X-Ray images. Five performance metrics are calculated, which are accuracy, sensitivity, specificity, correlation and error where the best obtained results are 0.9886, 0.0655, 0.99, 0.7246 and 0.01135, respectively.",
keywords = "Cervical Vertebrae, Medical Imaging, Segmentation, Tree-based Modelling, Watershed",
author = "Ikhsan, {Ili Ayuni Mohd} and Aini Hussain and Zulkifley, {Mohd Asyraf} and Aouache Mustapha",
year = "2015",
month = "9",
day = "1",
doi = "10.3993/jfbim00155",
language = "English",
volume = "8",
pages = "547--555",
journal = "Journal of Fiber Bioengineering and Informatics",
issn = "1940-8676",
publisher = "Textile Bioengineering and Informatics Society, The Hong Kong Polytechnic University",
number = "3",

}

TY - JOUR

T1 - Automated vertebrae extraction using watershed segmentation and tree-based modelling approach

AU - Ikhsan, Ili Ayuni Mohd

AU - Hussain, Aini

AU - Zulkifley, Mohd Asyraf

AU - Mustapha, Aouache

PY - 2015/9/1

Y1 - 2015/9/1

N2 - Vertebra segmentation and extraction are essential steps for automated vertebrae fracture assessment system. This study focuses on vertebra segmentation, which is a challenging task due to high noise and poor contrast of X-Ray images. The objective of this study is to develop and test an automated cervical vertebrae extraction to facilitate the medical researchers and physicians. The novelty of the proposed method is the combination of watershed segmentation and tree-based modelling algorithm. The proposed method has been successfully applied to a set of 50 cervical X-Ray images. Five performance metrics are calculated, which are accuracy, sensitivity, specificity, correlation and error where the best obtained results are 0.9886, 0.0655, 0.99, 0.7246 and 0.01135, respectively.

AB - Vertebra segmentation and extraction are essential steps for automated vertebrae fracture assessment system. This study focuses on vertebra segmentation, which is a challenging task due to high noise and poor contrast of X-Ray images. The objective of this study is to develop and test an automated cervical vertebrae extraction to facilitate the medical researchers and physicians. The novelty of the proposed method is the combination of watershed segmentation and tree-based modelling algorithm. The proposed method has been successfully applied to a set of 50 cervical X-Ray images. Five performance metrics are calculated, which are accuracy, sensitivity, specificity, correlation and error where the best obtained results are 0.9886, 0.0655, 0.99, 0.7246 and 0.01135, respectively.

KW - Cervical Vertebrae

KW - Medical Imaging

KW - Segmentation

KW - Tree-based Modelling

KW - Watershed

UR - http://www.scopus.com/inward/record.url?scp=84942904195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942904195&partnerID=8YFLogxK

U2 - 10.3993/jfbim00155

DO - 10.3993/jfbim00155

M3 - Article

AN - SCOPUS:84942904195

VL - 8

SP - 547

EP - 555

JO - Journal of Fiber Bioengineering and Informatics

JF - Journal of Fiber Bioengineering and Informatics

SN - 1940-8676

IS - 3

ER -