Automatic 3D vertebrae CT image active contour segmentation method based on weighted random forest

Liu Xia; Gan Quan; Li Bing; Liu Xiao; Wang Bo

doi:10.12086/oee.2020.200002

Article navigation > Opto-Electronic Engineering > 2020 Vol. 47 > No. 12 > 200002

Next Article Previous Article

Liu X, Gan Q, Li B, et al. Automatic 3D vertebrae CT image active contour segmentation method based on weighted random forest[J]. Opto-Electron Eng, 2020, 47(12): 200002. doi: 10.12086/oee.2020.200002

Citation:

Liu X, Gan Q, Li B, et al. Automatic 3D vertebrae CT image active contour segmentation method based on weighted random forest[J]. Opto-Electron Eng, 2020, 47(12): 200002. doi: 10.12086/oee.2020.200002

Automatic 3D vertebrae CT image active contour segmentation method based on weighted random forest

School of Automation, Harbin University of Science and Technology, Harbin, Heilongjiang 150080, China

Fund Project: Supported by National Natural Science Foundation of China (61172167) and Natural Science Foundation of Heilongjiang Province (QC2017076)

More Information

Corresponding author: Wang Bo, E-mail: hust_wb@126.com

Received Date 02 January 2020

Revised Date 16 April 2020

Published Date 15 December 2020

Abstract

Abstract

In order to solve the problems of sensitive initial contours and inaccurate segmentation caused by active contour segmentation of CT images, this paper proposes an automatic 3D vertebral CT active contour segmentation method combined weighted random forest called "WRF-AC". This method proposes a weighted random forest algorithm and an active contour energy function that includes edge energy. First, the weighted random forest is trained by extracting 3D Haar-like feature values of the vertebra CT, and the 'vertebra center' obtained is used as the initial contour of the segmentation. Then, the segmentation of the vertebra CT image is completed by solving the active contour energy function minimum containing the edge energy. The experimental results show that this method can segment the spine CT images more accurately and quickly on the same datasets to extract the vertebrae.
- 3D segmentation /
- CT images /
- weighted random forest /
- active contour

FullText(HTML)

References

[1]	Roth H R, Farag A, Lu L, et al. Deep convolutional networks for pancreas segmentation in CT imaging[J]. Proceedings of SPIE, 2015, 9413: 94131G. Google Scholar
[2]	Glocker B, Feulner J, Criminisi A, et al. Automatic localization and identification of vertebrae in arbitrary field-of-view CT scans[M]//Ayache N, Delingette H, Golland P, et al. Medical Image Computing and Computer-Assisted Intervention. Berlin Heidelberg: Springer, 2012: 590–598. Google Scholar
[3]	Kang Y, Engelke K, Kalender W A. A new accurate and precise 3-D segmentation method for skeletal structures in volumetric CT data[J]. IEEE Transactions Medical Imaging, 2003, 22(5): 586–598. doi: 10.1109/TMI.2003.812265 CrossRef Google Scholar
[4]	Lim P H, Bagci U, Bai L. Introducing Willmore flow into level set segmentation of spinal vertebrae[J]. IEEE Transactions on Biomedical Engineering, 2013, 60(1): 115–122. Google Scholar
[5]	Huang J Y, Jian F Z, Wu H, et al. An improved level set method for vertebra CT image segmentation[J]. Biomedical Engineering Online, 2013, 12: 48. doi: 10.1186/1475-925X-12-48 CrossRef Google Scholar
[6]	唐利明, 田学全, 黄大荣, 等.结合FCMS与变分水平集的图像分割模型[J].自动化学报, 2014, 40(6): 1233–1248. Google Scholar Tang L M, Tian X Q, Huang D R, et al. Image segmentation model combined with FCMS and variational level set[J]. Acta Automatica Sinica, 2014, 40(6): 1233–1248. Google Scholar
[7]	Criminisi A, Shotton J, Robertson D, et al. Regression forests for efficient anatomy detection and localization in CT studies[M]//Menze B, Langs G, Tu Z W, et al. Medical Computer Vision. Recognition Techniques and Applications in Medical Imaging. Berlin Heidelberg: Springer, 2010: 106–117. Google Scholar
[8]	Criminisi A, Robertson D, Konukoglu E, et al. Regression forests for efficient anatomy detection and localization in computed tomography scans[J]. Medical Image Analysis, 2013, 17(8): 1293–1303. doi: 10.1016/j.media.2013.01.001 CrossRef Google Scholar
[9]	Cuingnet R, Prevost R, Lesage D, et al. Automatic detection and segmentation of kidneys in 3D CT images using random forests[M]//Ayache N, Delingette H, Golland P, et al. Medical Image Computing and Computer-Assisted Intervention. Berlin Heidelberg: Springer, 2012: 66–74. Google Scholar
[10]	Klinder T, Ostermann J, Ehm M, et al. Automated model-based vertebra detection, identification, and segmentation in CT images[J]. Medical Image Analysis, 2009, 13(3): 471–482. Google Scholar
[11]	Huang S H, Chu Y H, Lai S H, et al. Learning-based vertebra detection and iterative normalized-cut segmentation for spinal MRI[J]. IEEE Transactions on Medical Imaging, 2009, 28(10): 1595–1605. doi: 10.1109/TMI.2009.2023362 CrossRef Google Scholar
[12]	Roberts M G, Cootes T F, Pacheco E, et al. Segmentation of lumbar vertebrae using part-based graphs and active appearance models[M]//Yang G Z, Hawkes D, Rueckert D, et al. Medical Image Computing and Computer-Assisted Intervention. Berlin Heidelberg: Springer, 2009: 1017–1024. Google Scholar
[13]	陈侃, 李彬, 田联房.基于模糊速度函数的活动轮廓模型的肺结节分割[J].自动化学报, 2013, 39(8): 1257–1264. Google Scholar Chen K, Li B, Tian L F. A segmentation algorithm of pulmonary nodules using active contour model based on fuzzy speed function[J]. Acta Automatica Sinica, 2013, 39(8): 1257–1264. Google Scholar
[14]	Thieu Q T, Luong M, Rocchisani J M, et al. Eﬃcient segmentation with the convex local-global fuzzy Gaussian distribution active contour for medical applications[J]. Annals of Mathematics and Artiﬁcial Intelligence, 2015, 75(1–2): 249–266. doi: 10.1007/s10472-014-9413-y CrossRef Google Scholar
[15]	孙文燕, 董恩清, 曹祝楼, 等.一种基于模糊主动轮廓的鲁棒局部分割方法[J].自动化学报, 2017, 43(4): 611–621. Google Scholar Sun W Y, Dong E Q, Cao Z L, et al. A robust local segmentation method based on fuzzy-energy based active contour[J]. Acta Automatica Sinica, 2017, 43(4): 611–621. Google Scholar
[16]	Viola P, Jones M J. Robust real-time face detection[J]. International Journal of Computer Vision, 2004, 57(2): 137–154. Google Scholar
[17]	Tu Z W, Zhou X S, Bogoni L, et al. Probabilistic 3D polyp detection in CT images: the role of sample alignment[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, 2006: 1544–1551. Google Scholar
[18]	Breiman L. Random forests[J]. Machine Learning, 2001, 45: 5–32. doi: 10.1023/A:1010933404324 CrossRef Google Scholar
[19]	李欣海.随机森林模型在分类与回归分析中的应用[J].应用昆虫学报, 2013, 50(4): 1190–1197. Google Scholar Li X H. Using "random forest" for classification and regression[J]. Chinese Journal of Applied Entomology, 2013, 50(4): 1190–1197. Google Scholar
[20]	Kass M, Witkin A, Terzopoulos D. Snake: active contour models[J]. International Journal of Computer Vision, 1988, 1(4): 321–331. Google Scholar
[21]	Malladi R, Sethian J A, Vemuri B C. Shape modeling with front propagation: a level set approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(2): 158–175. doi: 10.1109/34.368173 CrossRef Google Scholar
[22]	Hajiaghayi M, Groves E M, Jafarkhani H, et al. A 3-D active contour method for automated segmentation of the left ventricle from magnetic resonance images[J]. IEEE Transactions on Biomedical Engineering, 2017, 64(1): 134–144. Google Scholar
[23]	Osher S, Fedkiw R, Piechor K. Level set methods and dynamic implicit surfaces[J]. Applied Mechanics Reviews, 2004, 57(3): B15. Google Scholar
[24]	Forsberg D. Atlas-based segmentation of the thoracic and lumbar vertebrae[M]//Yao J H, Glocker B, Klinder T, et al. Recent Advances in Computational Methods and Clinical Applications for Spine Imaging. Cham: Springer, 2015: 215–220. Google Scholar
[25]	Hammernik K, Ebner T, Stern D, et al. Vertebrae segmentation in 3D CT Images based on a variational framework[M]// Yao J H, Glocker B, Klinder T, et al. Recent Advances in Computational Methods and Clinical Applications for Spine Imaging. Cham: Springer, 2015: 227–233. Google Scholar
[26]	Dice L R. Measures of the amount of ecologic association between species[J]. Ecology, 1945, 26(3): 297–302. Google Scholar
[27]	Castro-Mateos I, Pozo J M, Lazary A, et al. 3D vertebra segmentation by feature selection active shape model[M]//Yao J H, Glocker B, Klinder T, et al. Recent Advances in Computational Methods and Clinical Applications for Spine Imaging. Cham: Springer, 2015: 241–245. Google Scholar

Overview

Overview

Overview: Medical image segmentation has been widely used in medical image diagnosis technology and has become one of the indispensable means of clinical treatment. The use of computer processing to analyze spine CT images in modern medicine has become an important research direction, and has very important clinical application values. Due to the complicated structure of the vertebral body and the small difference, it is difficult for people to accurately extract the vertebral body of interest. In previous studies, we tried to manually set the initial contour directly to construct an interactive semi-automatic segmentation scheme. However, due to a large number of vertebrae in the human spine and the similar shape of the vertebrae, the manual setting of initial contour points requires a certain medical foundation and consumes much time. In order to solve the problems of sensitive initial contours and inaccurate segmentation caused by active contour segmentation of CT images, this paper proposes an automatic 3D vertebral CT active contour segmentation method combined weighted random forest called "WRF-AC". This method proposes a weighted random forest algorithm and an active contour energy function that includes edge energy. First, the weighted random forest is trained by extracting 3D Haar-like feature values of the vertebra CT, and the 'vertebra center' obtained is used as the initial contour of the segmentation. Then, the segmentation of the vertebra CT image is completed by solving the active contour energy function minimum containing the edge energy. The experimental results show that this method can segment the spine CT images more accurately and quickly on the same datasets to extract the vertebrae. Experimental results show that the average segmentation accuracy of the active contour segmentation method of 3D vertebra CT image fusion weighted random forest proposed in this paper can reach more than 92%. This method has certain advantages: it can automatically locate the center of the vertebrae and accurately segment the vertebral area; it is easy to obtain CT images of the spine, using the segmentation model proposed in this paper to segment the vertebral area, and combining the subsequent 3D reconstruction and 3D printing can easily help clinical applications and treatment. Due to the difficulty in collecting CT data of vertebrae, it is necessary to add more segmentation data for model training in the subsequent research to improve the segmentation accuracy of the segmentation model and achieve multi-level segmentation of the spine.