Knee MR image segmentation combining contextual constrained neural network and level set evolution

Haw Chang Lan, Tsai Rong Chang, Wen Ching Liao, Yi-Nung Chung, Pau Choo Chung

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

Abstract

Tracking the patella movement trajectory during the bending process of the knee is one essential step to knee pain diagnosis. In order for tracking patella, correct segmentation of the femur and patella from the axial knee MR image is indispensable. But the strong adhesion of the soft tissue around femur and patella, the gray-level similarities of adjacent organs, and the non-uniform gray intensity due to the degradation of the magnetic propagation make the MR image segmentation challenging. In this paper, we proposed a mechanism combining contextual constraint neural network (CCNN) and level set evolution to segment the femur and patella. The segmentation can be divided into two phases. In the first phase SOM and CCNN are applied to extract initial contours of the femur and patella. Consequently in the second phase, modified level set evolution is performed, with the extracted contours as the initial zero level set contour, to accomplish the segmentation of the femur and patella. Our experimental results show that the femur and patella can be correctly segmented for tracking patella movement.

Original languageEnglish
Title of host publication2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings
Pages271-277
Number of pages7
DOIs
Publication statusPublished - 2009 Jul 20
Event2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Nashville, TN, United States
Duration: 2009 Mar 302009 Apr 2

Publication series

Name2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings

Other

Other2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009
CountryUnited States
CityNashville, TN
Period09-03-3009-04-02

Fingerprint

Patella
Image segmentation
Knee
Neural networks
Femur
Adhesion
Trajectories
Tissue
Degradation
Tissue Adhesions
Pain

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Artificial Intelligence
  • Computational Theory and Mathematics

Cite this

Lan, H. C., Chang, T. R., Liao, W. C., Chung, Y-N., & Chung, P. C. (2009). Knee MR image segmentation combining contextual constrained neural network and level set evolution. In 2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings (pp. 271-277). [4925738] (2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings). https://doi.org/10.1109/CIBCB.2009.4925738
Lan, Haw Chang ; Chang, Tsai Rong ; Liao, Wen Ching ; Chung, Yi-Nung ; Chung, Pau Choo. / Knee MR image segmentation combining contextual constrained neural network and level set evolution. 2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings. 2009. pp. 271-277 (2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings).
@inproceedings{599679fdbb7e42d19d271705311262b4,
title = "Knee MR image segmentation combining contextual constrained neural network and level set evolution",
abstract = "Tracking the patella movement trajectory during the bending process of the knee is one essential step to knee pain diagnosis. In order for tracking patella, correct segmentation of the femur and patella from the axial knee MR image is indispensable. But the strong adhesion of the soft tissue around femur and patella, the gray-level similarities of adjacent organs, and the non-uniform gray intensity due to the degradation of the magnetic propagation make the MR image segmentation challenging. In this paper, we proposed a mechanism combining contextual constraint neural network (CCNN) and level set evolution to segment the femur and patella. The segmentation can be divided into two phases. In the first phase SOM and CCNN are applied to extract initial contours of the femur and patella. Consequently in the second phase, modified level set evolution is performed, with the extracted contours as the initial zero level set contour, to accomplish the segmentation of the femur and patella. Our experimental results show that the femur and patella can be correctly segmented for tracking patella movement.",
author = "Lan, {Haw Chang} and Chang, {Tsai Rong} and Liao, {Wen Ching} and Yi-Nung Chung and Chung, {Pau Choo}",
year = "2009",
month = "7",
day = "20",
doi = "10.1109/CIBCB.2009.4925738",
language = "English",
isbn = "9781424427567",
series = "2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings",
pages = "271--277",
booktitle = "2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings",

}

Lan, HC, Chang, TR, Liao, WC, Chung, Y-N & Chung, PC 2009, Knee MR image segmentation combining contextual constrained neural network and level set evolution. in 2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings., 4925738, 2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings, pp. 271-277, 2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009, Nashville, TN, United States, 09-03-30. https://doi.org/10.1109/CIBCB.2009.4925738

Knee MR image segmentation combining contextual constrained neural network and level set evolution. / Lan, Haw Chang; Chang, Tsai Rong; Liao, Wen Ching; Chung, Yi-Nung; Chung, Pau Choo.

2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings. 2009. p. 271-277 4925738 (2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings).

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

TY - GEN

T1 - Knee MR image segmentation combining contextual constrained neural network and level set evolution

AU - Lan, Haw Chang

AU - Chang, Tsai Rong

AU - Liao, Wen Ching

AU - Chung, Yi-Nung

AU - Chung, Pau Choo

PY - 2009/7/20

Y1 - 2009/7/20

N2 - Tracking the patella movement trajectory during the bending process of the knee is one essential step to knee pain diagnosis. In order for tracking patella, correct segmentation of the femur and patella from the axial knee MR image is indispensable. But the strong adhesion of the soft tissue around femur and patella, the gray-level similarities of adjacent organs, and the non-uniform gray intensity due to the degradation of the magnetic propagation make the MR image segmentation challenging. In this paper, we proposed a mechanism combining contextual constraint neural network (CCNN) and level set evolution to segment the femur and patella. The segmentation can be divided into two phases. In the first phase SOM and CCNN are applied to extract initial contours of the femur and patella. Consequently in the second phase, modified level set evolution is performed, with the extracted contours as the initial zero level set contour, to accomplish the segmentation of the femur and patella. Our experimental results show that the femur and patella can be correctly segmented for tracking patella movement.

AB - Tracking the patella movement trajectory during the bending process of the knee is one essential step to knee pain diagnosis. In order for tracking patella, correct segmentation of the femur and patella from the axial knee MR image is indispensable. But the strong adhesion of the soft tissue around femur and patella, the gray-level similarities of adjacent organs, and the non-uniform gray intensity due to the degradation of the magnetic propagation make the MR image segmentation challenging. In this paper, we proposed a mechanism combining contextual constraint neural network (CCNN) and level set evolution to segment the femur and patella. The segmentation can be divided into two phases. In the first phase SOM and CCNN are applied to extract initial contours of the femur and patella. Consequently in the second phase, modified level set evolution is performed, with the extracted contours as the initial zero level set contour, to accomplish the segmentation of the femur and patella. Our experimental results show that the femur and patella can be correctly segmented for tracking patella movement.

UR - http://www.scopus.com/inward/record.url?scp=67650363720&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650363720&partnerID=8YFLogxK

U2 - 10.1109/CIBCB.2009.4925738

DO - 10.1109/CIBCB.2009.4925738

M3 - Conference contribution

AN - SCOPUS:67650363720

SN - 9781424427567

T3 - 2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings

SP - 271

EP - 277

BT - 2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings

ER -

Lan HC, Chang TR, Liao WC, Chung Y-N, Chung PC. Knee MR image segmentation combining contextual constrained neural network and level set evolution. In 2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings. 2009. p. 271-277. 4925738. (2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2009 - Proceedings). https://doi.org/10.1109/CIBCB.2009.4925738