Segmentation of carpal bones using gradient inverse coefficient of variation with dynamic programming method

Research output: Contribution to journalArticle

Abstract

Segmentation of the carpal bones (CBs) especially for children above seven years old is a challenging task in computer vision mainly because of poor definitions of the bone contours and the occurrence of the partial overlapping of the bones. Although active contour methods are widely employed in image bone segmentation, they are sensitive to initialization and have limitation in segmenting overlapping objects. Thus, there is a need for a robust segmentation method for bone segmentation. This paper presents an automatic active boundary-based segmentation method, gradient inverse coefficient of variation, based on dynamic programming (DP-GICOV) method to segment carpal bones on radiographic images of children age 5 to 8 years old. A mapping procedure is designed based on a priori knowledge about the natural growth and the arrangement of carpal bones in human body. The accuracy of the DP-GICOV is compared qualitatively and quantitatively with the de-regularized level set (DRLS) and multi-scale gradient vector flow (MGVF) on a dataset of 20 images of carpal bones from University of Southern California. The presented method is capable to detect the bone boundaries fast and accurate. Results show that the DP-GICOV is highly accurate especially for overlapping bones, which is more than 85% in many cases, and it requires minimal user's intervention. This method has produced a promised result in overcoming both issues faced by active contours method; initialization and overlapping objects.

Original languageEnglish
Pages (from-to)73-80
Number of pages8
JournalInternational Journal on Advanced Science, Engineering and Information Technology
Volume9
Issue number1
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Carpal Bones
dynamic programming
Dynamic programming
Bone
bones
Bone and Bones
methodology
Human Body
Gradient methods
computer vision
Computer vision

Keywords

  • Active contour
  • Carpal bone
  • Dynamic programming
  • Gradient inverse coefficient of variation
  • Segmentation

ASJC Scopus subject areas

  • Computer Science(all)
  • Agricultural and Biological Sciences(all)
  • Engineering(all)

Cite this

@article{440e615b71134f6182bab98ee9b4d7b3,
title = "Segmentation of carpal bones using gradient inverse coefficient of variation with dynamic programming method",
abstract = "Segmentation of the carpal bones (CBs) especially for children above seven years old is a challenging task in computer vision mainly because of poor definitions of the bone contours and the occurrence of the partial overlapping of the bones. Although active contour methods are widely employed in image bone segmentation, they are sensitive to initialization and have limitation in segmenting overlapping objects. Thus, there is a need for a robust segmentation method for bone segmentation. This paper presents an automatic active boundary-based segmentation method, gradient inverse coefficient of variation, based on dynamic programming (DP-GICOV) method to segment carpal bones on radiographic images of children age 5 to 8 years old. A mapping procedure is designed based on a priori knowledge about the natural growth and the arrangement of carpal bones in human body. The accuracy of the DP-GICOV is compared qualitatively and quantitatively with the de-regularized level set (DRLS) and multi-scale gradient vector flow (MGVF) on a dataset of 20 images of carpal bones from University of Southern California. The presented method is capable to detect the bone boundaries fast and accurate. Results show that the DP-GICOV is highly accurate especially for overlapping bones, which is more than 85{\%} in many cases, and it requires minimal user's intervention. This method has produced a promised result in overcoming both issues faced by active contours method; initialization and overlapping objects.",
keywords = "Active contour, Carpal bone, Dynamic programming, Gradient inverse coefficient of variation, Segmentation",
author = "Sadiah Jantan and Muad, {Anuar Mikdad} and Aini Hussain",
year = "2019",
month = "1",
day = "1",
doi = "10.18517/ijaseit.9.1.4455",
language = "English",
volume = "9",
pages = "73--80",
journal = "International Journal on Advanced Science, Engineering and Information Technology",
issn = "2088-5334",
publisher = "INSIGHT - Indonesian Society for Knowledge and Human Development",
number = "1",

}

TY - JOUR

T1 - Segmentation of carpal bones using gradient inverse coefficient of variation with dynamic programming method

AU - Jantan, Sadiah

AU - Muad, Anuar Mikdad

AU - Hussain, Aini

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Segmentation of the carpal bones (CBs) especially for children above seven years old is a challenging task in computer vision mainly because of poor definitions of the bone contours and the occurrence of the partial overlapping of the bones. Although active contour methods are widely employed in image bone segmentation, they are sensitive to initialization and have limitation in segmenting overlapping objects. Thus, there is a need for a robust segmentation method for bone segmentation. This paper presents an automatic active boundary-based segmentation method, gradient inverse coefficient of variation, based on dynamic programming (DP-GICOV) method to segment carpal bones on radiographic images of children age 5 to 8 years old. A mapping procedure is designed based on a priori knowledge about the natural growth and the arrangement of carpal bones in human body. The accuracy of the DP-GICOV is compared qualitatively and quantitatively with the de-regularized level set (DRLS) and multi-scale gradient vector flow (MGVF) on a dataset of 20 images of carpal bones from University of Southern California. The presented method is capable to detect the bone boundaries fast and accurate. Results show that the DP-GICOV is highly accurate especially for overlapping bones, which is more than 85% in many cases, and it requires minimal user's intervention. This method has produced a promised result in overcoming both issues faced by active contours method; initialization and overlapping objects.

AB - Segmentation of the carpal bones (CBs) especially for children above seven years old is a challenging task in computer vision mainly because of poor definitions of the bone contours and the occurrence of the partial overlapping of the bones. Although active contour methods are widely employed in image bone segmentation, they are sensitive to initialization and have limitation in segmenting overlapping objects. Thus, there is a need for a robust segmentation method for bone segmentation. This paper presents an automatic active boundary-based segmentation method, gradient inverse coefficient of variation, based on dynamic programming (DP-GICOV) method to segment carpal bones on radiographic images of children age 5 to 8 years old. A mapping procedure is designed based on a priori knowledge about the natural growth and the arrangement of carpal bones in human body. The accuracy of the DP-GICOV is compared qualitatively and quantitatively with the de-regularized level set (DRLS) and multi-scale gradient vector flow (MGVF) on a dataset of 20 images of carpal bones from University of Southern California. The presented method is capable to detect the bone boundaries fast and accurate. Results show that the DP-GICOV is highly accurate especially for overlapping bones, which is more than 85% in many cases, and it requires minimal user's intervention. This method has produced a promised result in overcoming both issues faced by active contours method; initialization and overlapping objects.

KW - Active contour

KW - Carpal bone

KW - Dynamic programming

KW - Gradient inverse coefficient of variation

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85062431079&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062431079&partnerID=8YFLogxK

U2 - 10.18517/ijaseit.9.1.4455

DO - 10.18517/ijaseit.9.1.4455

M3 - Article

VL - 9

SP - 73

EP - 80

JO - International Journal on Advanced Science, Engineering and Information Technology

JF - International Journal on Advanced Science, Engineering and Information Technology

SN - 2088-5334

IS - 1

ER -