Multilabel graph based approach for knee cartilage segmentation: Data from the osteoarthritis initiative

Hong Seng Gan; Tian Swee Tan; Khairil Amir Sayuti; Ahmad Helmy Abdul Karim; Mohammed Rafiq Abdul Kadir

doi:10.1109/IECBES.2014.7047487

Multilabel graph based approach for knee cartilage segmentation: Data from the osteoarthritis initiative

Hong Seng Gan^*
, Tian Swee Tan
, Khairil Amir Sayuti
, Ahmad Helmy Abdul Karim
, Mohammed Rafiq Abdul Kadir

^*Corresponding author for this work

Universiti Teknologi Malaysia
Universiti Sains Malaysia

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

15 Citations (Scopus)

Abstract

Knee osteoarthritis is the second most dreadful disease after cardiovascular diseases. Affected patients will not have any effective cure and face the risk of undergoing total knee replacement in chronic stage. Quantitative analysis enhances our understanding of the pathophysiology of osteoarthritis. Nonetheless, manual segmentation is notorious for time- and resource-intensive. Hence, we propose a multilabel, semiautomated segmentation method based on random walks to facilitate the segmentation process. Random walks method is robust to noise, allows multiple objects segmentation and achieves global minimum solution. Our experiment results indicated that random walks achieved greater efficiency than manual segmentation while preserved the quality of knee cartilage segmentation as measured by the Dice's coefficient.

Original language	English
Title of host publication	IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences
Subtitle of host publication	"Miri, Where Engineering in Medicine and Biology and Humanity Meet"
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	210-213
Number of pages	4
ISBN (Electronic)	9781479940844
DOIs	https://doi.org/10.1109/IECBES.2014.7047487
Publication status	Published - 2014
Externally published	Yes
Event	3rd IEEE Conference on Biomedical Engineering and Sciences, IECBES 2014 - Kuala Lumpur, Malaysia Duration: 8 Dec 2014 → 10 Dec 2014

Publication series

Name	IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet"

Conference

Conference	3rd IEEE Conference on Biomedical Engineering and Sciences, IECBES 2014
Country/Territory	Malaysia
City	Kuala Lumpur
Period	8/12/14 → 10/12/14

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1109/IECBES.2014.7047487

Cite this

Gan, H. S., Tan, T. S., Sayuti, K. A., Karim, A. H. A., & Kadir, M. R. A. (2014). Multilabel graph based approach for knee cartilage segmentation: Data from the osteoarthritis initiative. In IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet" (pp. 210-213). Article 7047487 (IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet"). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IECBES.2014.7047487

Gan, Hong Seng ; Tan, Tian Swee ; Sayuti, Khairil Amir et al. / Multilabel graph based approach for knee cartilage segmentation : Data from the osteoarthritis initiative. IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet". Institute of Electrical and Electronics Engineers Inc., 2014. pp. 210-213 (IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet").

@inproceedings{c3a62e939f7c413f9cc1fbb0fe781173,

title = "Multilabel graph based approach for knee cartilage segmentation: Data from the osteoarthritis initiative",

abstract = "Knee osteoarthritis is the second most dreadful disease after cardiovascular diseases. Affected patients will not have any effective cure and face the risk of undergoing total knee replacement in chronic stage. Quantitative analysis enhances our understanding of the pathophysiology of osteoarthritis. Nonetheless, manual segmentation is notorious for time- and resource-intensive. Hence, we propose a multilabel, semiautomated segmentation method based on random walks to facilitate the segmentation process. Random walks method is robust to noise, allows multiple objects segmentation and achieves global minimum solution. Our experiment results indicated that random walks achieved greater efficiency than manual segmentation while preserved the quality of knee cartilage segmentation as measured by the Dice's coefficient.",

author = "Gan, \{Hong Seng\} and Tan, \{Tian Swee\} and Sayuti, \{Khairil Amir\} and Karim, \{Ahmad Helmy Abdul\} and Kadir, \{Mohammed Rafiq Abdul\}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 3rd IEEE Conference on Biomedical Engineering and Sciences, IECBES 2014 ; Conference date: 08-12-2014 Through 10-12-2014",

year = "2014",

doi = "10.1109/IECBES.2014.7047487",

language = "English",

series = "IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: {"}Miri, Where Engineering in Medicine and Biology and Humanity Meet{"}",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "210--213",

booktitle = "IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences",

}

Gan, HS, Tan, TS, Sayuti, KA, Karim, AHA & Kadir, MRA 2014, Multilabel graph based approach for knee cartilage segmentation: Data from the osteoarthritis initiative. in IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet"., 7047487, IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet", Institute of Electrical and Electronics Engineers Inc., pp. 210-213, 3rd IEEE Conference on Biomedical Engineering and Sciences, IECBES 2014, Kuala Lumpur, Malaysia, 8/12/14. https://doi.org/10.1109/IECBES.2014.7047487

Multilabel graph based approach for knee cartilage segmentation: Data from the osteoarthritis initiative. / Gan, Hong Seng; Tan, Tian Swee; Sayuti, Khairil Amir et al.
IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet". Institute of Electrical and Electronics Engineers Inc., 2014. p. 210-213 7047487 (IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet").

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Multilabel graph based approach for knee cartilage segmentation

T2 - 3rd IEEE Conference on Biomedical Engineering and Sciences, IECBES 2014

AU - Gan, Hong Seng

AU - Tan, Tian Swee

AU - Sayuti, Khairil Amir

AU - Karim, Ahmad Helmy Abdul

AU - Kadir, Mohammed Rafiq Abdul

PY - 2014

Y1 - 2014

N2 - Knee osteoarthritis is the second most dreadful disease after cardiovascular diseases. Affected patients will not have any effective cure and face the risk of undergoing total knee replacement in chronic stage. Quantitative analysis enhances our understanding of the pathophysiology of osteoarthritis. Nonetheless, manual segmentation is notorious for time- and resource-intensive. Hence, we propose a multilabel, semiautomated segmentation method based on random walks to facilitate the segmentation process. Random walks method is robust to noise, allows multiple objects segmentation and achieves global minimum solution. Our experiment results indicated that random walks achieved greater efficiency than manual segmentation while preserved the quality of knee cartilage segmentation as measured by the Dice's coefficient.

AB - Knee osteoarthritis is the second most dreadful disease after cardiovascular diseases. Affected patients will not have any effective cure and face the risk of undergoing total knee replacement in chronic stage. Quantitative analysis enhances our understanding of the pathophysiology of osteoarthritis. Nonetheless, manual segmentation is notorious for time- and resource-intensive. Hence, we propose a multilabel, semiautomated segmentation method based on random walks to facilitate the segmentation process. Random walks method is robust to noise, allows multiple objects segmentation and achieves global minimum solution. Our experiment results indicated that random walks achieved greater efficiency than manual segmentation while preserved the quality of knee cartilage segmentation as measured by the Dice's coefficient.

UR - https://www.scopus.com/pages/publications/84925652634

U2 - 10.1109/IECBES.2014.7047487

DO - 10.1109/IECBES.2014.7047487

M3 - Conference Proceeding

AN - SCOPUS:84925652634

T3 - IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet"

SP - 210

EP - 213

BT - IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 8 December 2014 through 10 December 2014

ER -

Gan HS, Tan TS, Sayuti KA, Karim AHA, Kadir MRA. Multilabel graph based approach for knee cartilage segmentation: Data from the osteoarthritis initiative. In IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet". Institute of Electrical and Electronics Engineers Inc. 2014. p. 210-213. 7047487. (IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet"). doi: 10.1109/IECBES.2014.7047487

Multilabel graph based approach for knee cartilage segmentation: Data from the osteoarthritis initiative

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this