Shape-based boundary segmentation assessment for cervical vertebrae classification

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

2 Citations (Scopus)

Abstract

Shape-based boundary representation is a critical component in medical imaging-based diagnosis system. Furthermore, accurate boundary representation is also essential in getting good segmentation, feature indexing and classification. This work concentrates on cervical vertebra distortion across the anterior boundary to detect anterior osteophytes and identify its severity. A suitable shape representation, which defines the vertebrae shape boundary must be determined prior to the cervical vertebra model can be constructed. Therefore, two different shape-based representations for vertebral segmentation using active shape model are analysed, which are 9-anatomical point representation (9-APR) and B-spline representation (BSR). The aims is to compare and quantify the precision and accuracy performance of the segmented vertebra with the help of orientation histogram-based indexing and multi-layer perception based on ten-fold cross validation (MLP-TFCV) classifier. Experimental results are assessed based on the segmented boundary outline by using ROC and AUC curves. The results show that the performance of both boundary representations are almost similar where B-SR has a small advantage compared to the 9-APR. The system can be further improved by introducing a statistical sampling method of the anterior points instead of the whole vertebra.

Original languageEnglish
Title of host publicationProceedings - 2015 International Electronics Symposium: Emerging Technology in Electronic and Information, IES 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages41-46
Number of pages6
ISBN (Print)9781467393454
DOIs
Publication statusPublished - 12 Jan 2016
Event17th International Electronics Symposium, IES 2015 - Surabaya, Indonesia
Duration: 29 Sep 201530 Sep 2015

Other

Other17th International Electronics Symposium, IES 2015
CountryIndonesia
CitySurabaya
Period29/9/1530/9/15

Fingerprint

Medical imaging
Splines
Classifiers
Sampling

Keywords

  • 9-anatomical Point Representation
  • ASM Segmentation
  • B-spline Representation
  • Cervical Vertebra
  • MLP-TFCV

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Mustapha, A., Hussain, A., Zulkifley, M. A., & Ibrahim, M. F. (2016). Shape-based boundary segmentation assessment for cervical vertebrae classification. In Proceedings - 2015 International Electronics Symposium: Emerging Technology in Electronic and Information, IES 2015 (pp. 41-46). [7380811] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ELECSYM.2015.7380811

Shape-based boundary segmentation assessment for cervical vertebrae classification. / Mustapha, Aouache; Hussain, Aini; Zulkifley, Mohd Asyraf; Ibrahim, Mohd Faisal.

Proceedings - 2015 International Electronics Symposium: Emerging Technology in Electronic and Information, IES 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 41-46 7380811.

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

Mustapha, A, Hussain, A, Zulkifley, MA & Ibrahim, MF 2016, Shape-based boundary segmentation assessment for cervical vertebrae classification. in Proceedings - 2015 International Electronics Symposium: Emerging Technology in Electronic and Information, IES 2015., 7380811, Institute of Electrical and Electronics Engineers Inc., pp. 41-46, 17th International Electronics Symposium, IES 2015, Surabaya, Indonesia, 29/9/15. https://doi.org/10.1109/ELECSYM.2015.7380811
Mustapha A, Hussain A, Zulkifley MA, Ibrahim MF. Shape-based boundary segmentation assessment for cervical vertebrae classification. In Proceedings - 2015 International Electronics Symposium: Emerging Technology in Electronic and Information, IES 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 41-46. 7380811 https://doi.org/10.1109/ELECSYM.2015.7380811
Mustapha, Aouache ; Hussain, Aini ; Zulkifley, Mohd Asyraf ; Ibrahim, Mohd Faisal. / Shape-based boundary segmentation assessment for cervical vertebrae classification. Proceedings - 2015 International Electronics Symposium: Emerging Technology in Electronic and Information, IES 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 41-46
@inproceedings{84c77ce242d54aaba02872840f261f83,
title = "Shape-based boundary segmentation assessment for cervical vertebrae classification",
abstract = "Shape-based boundary representation is a critical component in medical imaging-based diagnosis system. Furthermore, accurate boundary representation is also essential in getting good segmentation, feature indexing and classification. This work concentrates on cervical vertebra distortion across the anterior boundary to detect anterior osteophytes and identify its severity. A suitable shape representation, which defines the vertebrae shape boundary must be determined prior to the cervical vertebra model can be constructed. Therefore, two different shape-based representations for vertebral segmentation using active shape model are analysed, which are 9-anatomical point representation (9-APR) and B-spline representation (BSR). The aims is to compare and quantify the precision and accuracy performance of the segmented vertebra with the help of orientation histogram-based indexing and multi-layer perception based on ten-fold cross validation (MLP-TFCV) classifier. Experimental results are assessed based on the segmented boundary outline by using ROC and AUC curves. The results show that the performance of both boundary representations are almost similar where B-SR has a small advantage compared to the 9-APR. The system can be further improved by introducing a statistical sampling method of the anterior points instead of the whole vertebra.",
keywords = "9-anatomical Point Representation, ASM Segmentation, B-spline Representation, Cervical Vertebra, MLP-TFCV",
author = "Aouache Mustapha and Aini Hussain and Zulkifley, {Mohd Asyraf} and Ibrahim, {Mohd Faisal}",
year = "2016",
month = "1",
day = "12",
doi = "10.1109/ELECSYM.2015.7380811",
language = "English",
isbn = "9781467393454",
pages = "41--46",
booktitle = "Proceedings - 2015 International Electronics Symposium: Emerging Technology in Electronic and Information, IES 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Shape-based boundary segmentation assessment for cervical vertebrae classification

AU - Mustapha, Aouache

AU - Hussain, Aini

AU - Zulkifley, Mohd Asyraf

AU - Ibrahim, Mohd Faisal

PY - 2016/1/12

Y1 - 2016/1/12

N2 - Shape-based boundary representation is a critical component in medical imaging-based diagnosis system. Furthermore, accurate boundary representation is also essential in getting good segmentation, feature indexing and classification. This work concentrates on cervical vertebra distortion across the anterior boundary to detect anterior osteophytes and identify its severity. A suitable shape representation, which defines the vertebrae shape boundary must be determined prior to the cervical vertebra model can be constructed. Therefore, two different shape-based representations for vertebral segmentation using active shape model are analysed, which are 9-anatomical point representation (9-APR) and B-spline representation (BSR). The aims is to compare and quantify the precision and accuracy performance of the segmented vertebra with the help of orientation histogram-based indexing and multi-layer perception based on ten-fold cross validation (MLP-TFCV) classifier. Experimental results are assessed based on the segmented boundary outline by using ROC and AUC curves. The results show that the performance of both boundary representations are almost similar where B-SR has a small advantage compared to the 9-APR. The system can be further improved by introducing a statistical sampling method of the anterior points instead of the whole vertebra.

AB - Shape-based boundary representation is a critical component in medical imaging-based diagnosis system. Furthermore, accurate boundary representation is also essential in getting good segmentation, feature indexing and classification. This work concentrates on cervical vertebra distortion across the anterior boundary to detect anterior osteophytes and identify its severity. A suitable shape representation, which defines the vertebrae shape boundary must be determined prior to the cervical vertebra model can be constructed. Therefore, two different shape-based representations for vertebral segmentation using active shape model are analysed, which are 9-anatomical point representation (9-APR) and B-spline representation (BSR). The aims is to compare and quantify the precision and accuracy performance of the segmented vertebra with the help of orientation histogram-based indexing and multi-layer perception based on ten-fold cross validation (MLP-TFCV) classifier. Experimental results are assessed based on the segmented boundary outline by using ROC and AUC curves. The results show that the performance of both boundary representations are almost similar where B-SR has a small advantage compared to the 9-APR. The system can be further improved by introducing a statistical sampling method of the anterior points instead of the whole vertebra.

KW - 9-anatomical Point Representation

KW - ASM Segmentation

KW - B-spline Representation

KW - Cervical Vertebra

KW - MLP-TFCV

UR - http://www.scopus.com/inward/record.url?scp=84969941177&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969941177&partnerID=8YFLogxK

U2 - 10.1109/ELECSYM.2015.7380811

DO - 10.1109/ELECSYM.2015.7380811

M3 - Conference contribution

SN - 9781467393454

SP - 41

EP - 46

BT - Proceedings - 2015 International Electronics Symposium: Emerging Technology in Electronic and Information, IES 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -