Vertebrae segmentation from X-ray images using convolutional neural network

Min Jun Fu, Chii-Jeng Lin, Yung-Nien Sun, Chan Pang Kuok, Ming Huwi Horng

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

Abstract

The X-ray examination can effectively help for the diagnosis and analysis of spinal diseases because it possesses the properties of fast, non-invasive, low radiation dose and low cost. In order to obtain the valuable quantitative information of the spine, the automated computer aided tools are developed. The segmentation of vertebrae is an important step to analyze the disease severity from the spinal X-ray images. Although there were numerous studies for automatic vertebrae segmentation in the literature, the segmentation of vertebrae from the frontal X-ray images is still a challenging topic. In this paper, a hybrid method is proposed to segment the thoracic and lumbar vertebrae from an anteroposterior (AP) full spine X-ray image. We apply image processing techniques to detect the vertebral regions and then use the convolutional neural network (CNN) to segment the vertebrae. The segmentation performance using the proposed method is remarkably high with DSC value of 0.941.

Original languageEnglish
Title of host publicationIHIP 2018 - 2018 International Conference on Information Hiding and Image Processing
PublisherAssociation for Computing Machinery
Pages57-61
Number of pages5
ISBN (Electronic)9781450365468
DOIs
Publication statusPublished - 2018 Sep 22
Event1st International Conference on Information Hiding and Image Processing, IHIP 2018 - Manchester, United Kingdom
Duration: 2018 Sep 222018 Sep 24

Publication series

NameACM International Conference Proceeding Series

Conference

Conference1st International Conference on Information Hiding and Image Processing, IHIP 2018
CountryUnited Kingdom
CityManchester
Period18-09-2218-09-24

Fingerprint

Neural networks
X rays
Dosimetry
Image processing
Costs

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Cite this

Fu, M. J., Lin, C-J., Sun, Y-N., Kuok, C. P., & Horng, M. H. (2018). Vertebrae segmentation from X-ray images using convolutional neural network. In IHIP 2018 - 2018 International Conference on Information Hiding and Image Processing (pp. 57-61). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3292425.3293463
Fu, Min Jun ; Lin, Chii-Jeng ; Sun, Yung-Nien ; Kuok, Chan Pang ; Horng, Ming Huwi. / Vertebrae segmentation from X-ray images using convolutional neural network. IHIP 2018 - 2018 International Conference on Information Hiding and Image Processing. Association for Computing Machinery, 2018. pp. 57-61 (ACM International Conference Proceeding Series).
@inproceedings{2aba0233d15741019b39289bfb1fe568,
title = "Vertebrae segmentation from X-ray images using convolutional neural network",
abstract = "The X-ray examination can effectively help for the diagnosis and analysis of spinal diseases because it possesses the properties of fast, non-invasive, low radiation dose and low cost. In order to obtain the valuable quantitative information of the spine, the automated computer aided tools are developed. The segmentation of vertebrae is an important step to analyze the disease severity from the spinal X-ray images. Although there were numerous studies for automatic vertebrae segmentation in the literature, the segmentation of vertebrae from the frontal X-ray images is still a challenging topic. In this paper, a hybrid method is proposed to segment the thoracic and lumbar vertebrae from an anteroposterior (AP) full spine X-ray image. We apply image processing techniques to detect the vertebral regions and then use the convolutional neural network (CNN) to segment the vertebrae. The segmentation performance using the proposed method is remarkably high with DSC value of 0.941.",
author = "Fu, {Min Jun} and Chii-Jeng Lin and Yung-Nien Sun and Kuok, {Chan Pang} and Horng, {Ming Huwi}",
year = "2018",
month = "9",
day = "22",
doi = "10.1145/3292425.3293463",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "57--61",
booktitle = "IHIP 2018 - 2018 International Conference on Information Hiding and Image Processing",

}

Fu, MJ, Lin, C-J, Sun, Y-N, Kuok, CP & Horng, MH 2018, Vertebrae segmentation from X-ray images using convolutional neural network. in IHIP 2018 - 2018 International Conference on Information Hiding and Image Processing. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 57-61, 1st International Conference on Information Hiding and Image Processing, IHIP 2018, Manchester, United Kingdom, 18-09-22. https://doi.org/10.1145/3292425.3293463

Vertebrae segmentation from X-ray images using convolutional neural network. / Fu, Min Jun; Lin, Chii-Jeng; Sun, Yung-Nien; Kuok, Chan Pang; Horng, Ming Huwi.

IHIP 2018 - 2018 International Conference on Information Hiding and Image Processing. Association for Computing Machinery, 2018. p. 57-61 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Vertebrae segmentation from X-ray images using convolutional neural network

AU - Fu, Min Jun

AU - Lin, Chii-Jeng

AU - Sun, Yung-Nien

AU - Kuok, Chan Pang

AU - Horng, Ming Huwi

PY - 2018/9/22

Y1 - 2018/9/22

N2 - The X-ray examination can effectively help for the diagnosis and analysis of spinal diseases because it possesses the properties of fast, non-invasive, low radiation dose and low cost. In order to obtain the valuable quantitative information of the spine, the automated computer aided tools are developed. The segmentation of vertebrae is an important step to analyze the disease severity from the spinal X-ray images. Although there were numerous studies for automatic vertebrae segmentation in the literature, the segmentation of vertebrae from the frontal X-ray images is still a challenging topic. In this paper, a hybrid method is proposed to segment the thoracic and lumbar vertebrae from an anteroposterior (AP) full spine X-ray image. We apply image processing techniques to detect the vertebral regions and then use the convolutional neural network (CNN) to segment the vertebrae. The segmentation performance using the proposed method is remarkably high with DSC value of 0.941.

AB - The X-ray examination can effectively help for the diagnosis and analysis of spinal diseases because it possesses the properties of fast, non-invasive, low radiation dose and low cost. In order to obtain the valuable quantitative information of the spine, the automated computer aided tools are developed. The segmentation of vertebrae is an important step to analyze the disease severity from the spinal X-ray images. Although there were numerous studies for automatic vertebrae segmentation in the literature, the segmentation of vertebrae from the frontal X-ray images is still a challenging topic. In this paper, a hybrid method is proposed to segment the thoracic and lumbar vertebrae from an anteroposterior (AP) full spine X-ray image. We apply image processing techniques to detect the vertebral regions and then use the convolutional neural network (CNN) to segment the vertebrae. The segmentation performance using the proposed method is remarkably high with DSC value of 0.941.

UR - http://www.scopus.com/inward/record.url?scp=85061546782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061546782&partnerID=8YFLogxK

U2 - 10.1145/3292425.3293463

DO - 10.1145/3292425.3293463

M3 - Conference contribution

AN - SCOPUS:85061546782

T3 - ACM International Conference Proceeding Series

SP - 57

EP - 61

BT - IHIP 2018 - 2018 International Conference on Information Hiding and Image Processing

PB - Association for Computing Machinery

ER -

Fu MJ, Lin C-J, Sun Y-N, Kuok CP, Horng MH. Vertebrae segmentation from X-ray images using convolutional neural network. In IHIP 2018 - 2018 International Conference on Information Hiding and Image Processing. Association for Computing Machinery. 2018. p. 57-61. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3292425.3293463