Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise

Zixun Huang; Liwen Wang; Frank H.F. Leung; Sunetra Banerjee; De Yang; Timothy Lee; Juan Lyu; Sai Ho Ling; Yong Ping Zheng

doi:10.1109/SMC42975.2020.9283335

Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise

Zixun Huang, Liwen Wang, Frank H.F. Leung, Sunetra Banerjee, De Yang, Timothy Lee, Juan Lyu, Sai Ho Ling, Yong Ping Zheng

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

8 Citations (Scopus)

Abstract

3D ultrasound imaging shows great promise for scoliosis diagnosis thanks to its low-costing, radiation-free and real-time characteristics. The key to accessing scoliosis by ultrasound imaging is to accurately segment the bone area and measure the scoliosis degree based on the symmetry of the bone features. The ultrasound images tend to contain many speckles and regular occlusion noise which is difficult, tedious and time-consuming for experts to find out the bony feature. In this paper, we propose a robust bone feature segmentation method based on the U-net structure for ultrasound spine Volume Projection Imaging (VPI) images. The proposed segmentation method introduces a total variance loss to reduce the sensitivity of the model to small-scale and regular occlusion noise. The proposed approach improves 2.3% of Dice score and 1% of AUC score as compared with the u-net model and shows high robustness to speckle and regular occlusion noise.

Original language	English
Title of host publication	2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1566-1571
Number of pages	6
Volume	2020-October
ISBN (Electronic)	9781728185262
DOIs	https://doi.org/10.1109/SMC42975.2020.9283335
Publication status	Published - 11 Oct 2020
Event	2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 - Toronto, Canada Duration: 11 Oct 2020 → 14 Oct 2020

Conference

Conference	2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
Country/Territory	Canada
City	Toronto
Period	11/10/20 → 14/10/20

Keywords

3-D ultrasound
bone feature segmentation
robustness
scoliosis
volume projection imaging

ASJC Scopus subject areas

Software
Control and Systems Engineering
Human-Computer Interaction
Computer Science Applications
Electrical and Electronic Engineering

More information

10.1109/SMC42975.2020.9283335

http://hdl.handle.net/10397/107119

Cite this

Huang, Z., Wang, L., Leung, F. H. F., Banerjee, S., Yang, D., Lee, T., Lyu, J., Ling, S. H., & Zheng, Y. P. (2020). Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise. In 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 (Vol. 2020-October, pp. 1566-1571). Article 9283335 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC42975.2020.9283335

@inproceedings{2f66107dc89c4ef7bc68cc579f80f50a,

title = "Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise",

abstract = "3D ultrasound imaging shows great promise for scoliosis diagnosis thanks to its low-costing, radiation-free and real-time characteristics. The key to accessing scoliosis by ultrasound imaging is to accurately segment the bone area and measure the scoliosis degree based on the symmetry of the bone features. The ultrasound images tend to contain many speckles and regular occlusion noise which is difficult, tedious and time-consuming for experts to find out the bony feature. In this paper, we propose a robust bone feature segmentation method based on the U-net structure for ultrasound spine Volume Projection Imaging (VPI) images. The proposed segmentation method introduces a total variance loss to reduce the sensitivity of the model to small-scale and regular occlusion noise. The proposed approach improves 2.3% of Dice score and 1% of AUC score as compared with the u-net model and shows high robustness to speckle and regular occlusion noise.",

keywords = "3-D ultrasound, bone feature segmentation, robustness, scoliosis, volume projection imaging",

author = "Zixun Huang and Liwen Wang and Leung, {Frank H.F.} and Sunetra Banerjee and De Yang and Timothy Lee and Juan Lyu and Ling, {Sai Ho} and Zheng, {Yong Ping}",

note = "Funding Information: The work described in this paper was partially supported by Hong Kong Research Grant Council Research Impact Fund (R5017-18), and a grant from The Hong Kong Polytechnic University. Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 ; Conference date: 11-10-2020 Through 14-10-2020",

year = "2020",

month = oct,

day = "11",

doi = "10.1109/SMC42975.2020.9283335",

language = "English",

volume = "2020-October",

pages = "1566--1571",

booktitle = "2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020",

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

}

Huang, Z, Wang, L, Leung, FHF, Banerjee, S, Yang, D, Lee, T, Lyu, J, Ling, SH & Zheng, YP 2020, Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise. in 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020. vol. 2020-October, 9283335, Institute of Electrical and Electronics Engineers Inc., pp. 1566-1571, 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020, Toronto, Canada, 11/10/20. https://doi.org/10.1109/SMC42975.2020.9283335

Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise. / Huang, Zixun; Wang, Liwen; Leung, Frank H.F. et al.
2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020. Vol. 2020-October Institute of Electrical and Electronics Engineers Inc., 2020. p. 1566-1571 9283335.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise

AU - Huang, Zixun

AU - Wang, Liwen

AU - Leung, Frank H.F.

AU - Banerjee, Sunetra

AU - Yang, De

AU - Lee, Timothy

AU - Lyu, Juan

AU - Ling, Sai Ho

AU - Zheng, Yong Ping

N1 - Funding Information: The work described in this paper was partially supported by Hong Kong Research Grant Council Research Impact Fund (R5017-18), and a grant from The Hong Kong Polytechnic University. Publisher Copyright: © 2020 IEEE.

PY - 2020/10/11

Y1 - 2020/10/11

N2 - 3D ultrasound imaging shows great promise for scoliosis diagnosis thanks to its low-costing, radiation-free and real-time characteristics. The key to accessing scoliosis by ultrasound imaging is to accurately segment the bone area and measure the scoliosis degree based on the symmetry of the bone features. The ultrasound images tend to contain many speckles and regular occlusion noise which is difficult, tedious and time-consuming for experts to find out the bony feature. In this paper, we propose a robust bone feature segmentation method based on the U-net structure for ultrasound spine Volume Projection Imaging (VPI) images. The proposed segmentation method introduces a total variance loss to reduce the sensitivity of the model to small-scale and regular occlusion noise. The proposed approach improves 2.3% of Dice score and 1% of AUC score as compared with the u-net model and shows high robustness to speckle and regular occlusion noise.

AB - 3D ultrasound imaging shows great promise for scoliosis diagnosis thanks to its low-costing, radiation-free and real-time characteristics. The key to accessing scoliosis by ultrasound imaging is to accurately segment the bone area and measure the scoliosis degree based on the symmetry of the bone features. The ultrasound images tend to contain many speckles and regular occlusion noise which is difficult, tedious and time-consuming for experts to find out the bony feature. In this paper, we propose a robust bone feature segmentation method based on the U-net structure for ultrasound spine Volume Projection Imaging (VPI) images. The proposed segmentation method introduces a total variance loss to reduce the sensitivity of the model to small-scale and regular occlusion noise. The proposed approach improves 2.3% of Dice score and 1% of AUC score as compared with the u-net model and shows high robustness to speckle and regular occlusion noise.

KW - 3-D ultrasound

KW - bone feature segmentation

KW - robustness

KW - scoliosis

KW - volume projection imaging

UR - http://www.scopus.com/inward/record.url?scp=85098843516&partnerID=8YFLogxK

U2 - 10.1109/SMC42975.2020.9283335

DO - 10.1109/SMC42975.2020.9283335

M3 - Conference article published in proceeding or book

AN - SCOPUS:85098843516

VL - 2020-October

SP - 1566

EP - 1571

BT - 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020

Y2 - 11 October 2020 through 14 October 2020

ER -

Huang Z, Wang L, Leung FHF, Banerjee S, Yang D, Lee T et al. Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise. In 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020. Vol. 2020-October. Institute of Electrical and Electronics Engineers Inc. 2020. p. 1566-1571. 9283335 doi: 10.1109/SMC42975.2020.9283335

Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this