Automatic extraction of vertebral endplates from scoliotic radiographs using customized filter

H. Anitha, A. K. Karunakar, K. V N Dinesh

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Purpose: The scoliosis diagnosing system needs radio-graphic information in terms of spinal curvature estimated using Cobb's definition. The evaluation process and treatment analysis depends on the reliability and reproducibility of the spine curvature in the frontal view. Methods: Manual identification of end vertebrae and other anatomical features required for the estimation of spinal curvature causes variability and unreliability at higher rate. This paper proposes an automated system to extract the required anatomical features using customized filter. The customized filter used in this paper is a combination of anisotropic, sigmoid and differential filter. Combination of these filters automatically extracts the anatomical features in terms of required vertebral endplates. Automatic identification of these endplates eliminates the human intervention involved in the quantification of Cobb angle. Results and Conclusions: Analysis of the results reveals significant difference between the observer variability between manual, computer assisted and computerized image understanding system in terms of inter and intra cross correlation coefficient ratio (ICCR).

Original languageEnglish
Pages (from-to)158-165
Number of pages8
JournalBiomedical Engineering Letters
Volume4
Issue number2
DOIs
Publication statusPublished - 2014

Fingerprint

Image understanding
Radio systems

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

@article{d9f44e3dfe774c60836cb6fd31db2d32,
title = "Automatic extraction of vertebral endplates from scoliotic radiographs using customized filter",
abstract = "Purpose: The scoliosis diagnosing system needs radio-graphic information in terms of spinal curvature estimated using Cobb's definition. The evaluation process and treatment analysis depends on the reliability and reproducibility of the spine curvature in the frontal view. Methods: Manual identification of end vertebrae and other anatomical features required for the estimation of spinal curvature causes variability and unreliability at higher rate. This paper proposes an automated system to extract the required anatomical features using customized filter. The customized filter used in this paper is a combination of anisotropic, sigmoid and differential filter. Combination of these filters automatically extracts the anatomical features in terms of required vertebral endplates. Automatic identification of these endplates eliminates the human intervention involved in the quantification of Cobb angle. Results and Conclusions: Analysis of the results reveals significant difference between the observer variability between manual, computer assisted and computerized image understanding system in terms of inter and intra cross correlation coefficient ratio (ICCR).",
author = "H. Anitha and Karunakar, {A. K.} and Dinesh, {K. V N}",
year = "2014",
doi = "10.1007/s13534-014-0129-z",
language = "English",
volume = "4",
pages = "158--165",
journal = "Biomedical Engineering Letters",
issn = "2093-9868",
publisher = "Springer Verlag",
number = "2",

}

Automatic extraction of vertebral endplates from scoliotic radiographs using customized filter. / Anitha, H.; Karunakar, A. K.; Dinesh, K. V N.

In: Biomedical Engineering Letters, Vol. 4, No. 2, 2014, p. 158-165.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic extraction of vertebral endplates from scoliotic radiographs using customized filter

AU - Anitha, H.

AU - Karunakar, A. K.

AU - Dinesh, K. V N

PY - 2014

Y1 - 2014

N2 - Purpose: The scoliosis diagnosing system needs radio-graphic information in terms of spinal curvature estimated using Cobb's definition. The evaluation process and treatment analysis depends on the reliability and reproducibility of the spine curvature in the frontal view. Methods: Manual identification of end vertebrae and other anatomical features required for the estimation of spinal curvature causes variability and unreliability at higher rate. This paper proposes an automated system to extract the required anatomical features using customized filter. The customized filter used in this paper is a combination of anisotropic, sigmoid and differential filter. Combination of these filters automatically extracts the anatomical features in terms of required vertebral endplates. Automatic identification of these endplates eliminates the human intervention involved in the quantification of Cobb angle. Results and Conclusions: Analysis of the results reveals significant difference between the observer variability between manual, computer assisted and computerized image understanding system in terms of inter and intra cross correlation coefficient ratio (ICCR).

AB - Purpose: The scoliosis diagnosing system needs radio-graphic information in terms of spinal curvature estimated using Cobb's definition. The evaluation process and treatment analysis depends on the reliability and reproducibility of the spine curvature in the frontal view. Methods: Manual identification of end vertebrae and other anatomical features required for the estimation of spinal curvature causes variability and unreliability at higher rate. This paper proposes an automated system to extract the required anatomical features using customized filter. The customized filter used in this paper is a combination of anisotropic, sigmoid and differential filter. Combination of these filters automatically extracts the anatomical features in terms of required vertebral endplates. Automatic identification of these endplates eliminates the human intervention involved in the quantification of Cobb angle. Results and Conclusions: Analysis of the results reveals significant difference between the observer variability between manual, computer assisted and computerized image understanding system in terms of inter and intra cross correlation coefficient ratio (ICCR).

UR - http://www.scopus.com/inward/record.url?scp=84904168967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904168967&partnerID=8YFLogxK

U2 - 10.1007/s13534-014-0129-z

DO - 10.1007/s13534-014-0129-z

M3 - Article

VL - 4

SP - 158

EP - 165

JO - Biomedical Engineering Letters

JF - Biomedical Engineering Letters

SN - 2093-9868

IS - 2

ER -