Abstract
Background: Automatic approach to vertebrae segmentation from computed tomography (CT) images is very important in clinical applications. As the intricate appearance and variable architecture of vertebrae across the population, cognate constructions in close vicinity, pathology, and the interconnection between vertebrae and ribs, it is a challenge to propose a 3D automatic vertebrae CT image segmentation method.
Objective: The purpose of this study was to propose an automatic multi-vertebrae segmentation method for spinal CT images.
Methods: Firstly, CLAHE-Threshold-Expansion was preprocessed to improve image quality and reduce input voxel points. Then, 3D coarse segmentation fully convolutional network and cascaded finely segmentation convolutional neural network were used to complete multi-vertebrae segmentation and classification.
Results: The results of this paper were compared with the other methods on the same datasets. Experimental results demonstrated that the Dice similarity coefficient (DSC) in this paper is 94.84%, higher than the V-net and 3D U-net.
Conclusion: Method of this paper has certain advantages in automatically and accurately segmenting vertebrae regions of CT images. Due to the easy acquisition of spine CT images. It was proven to be more conducive to clinical application of treatment that uses our segmentation model to obtain vertebrae regions, combining with the subsequent 3D reconstruction and printing work.
Keywords: CT Image, 3D vertebra segmentation, FCN, CNN, ribs, spine.
Graphical Abstract
[1]
Holger RR, Amal F, Le L, Evrim BT, Ronald MS. Deep convolutional networks for pancreas segmentation in CT imaging Medical Imaging 2015. 394131G
[2]
Glocker B, Feulner J, Criminisi A, Haynor DR, Konukoglu E. Automatic localization and identification of vertebrae in arbitrary field-of-view CT scans.Med Image Comput Comput Assist Interv. 2012; 15: pp. (Pt 3)590-8.
[http://dx.doi.org/10.1007/978-3-642-33454-2_73] [PMID: 23286179]
[http://dx.doi.org/10.1007/978-3-642-33454-2_73] [PMID: 23286179]
[3]
Sun F, He W, Fan J 2D. Otsu segmentation algorithm based on simulated annealing genetic algorithm for iced-cable. International forum on information technology and applications; .
Sichuan, China. IEEE Xplore
2009.
[4]
Kang CC, Wang WJ, Kang CH. Image segmentation with complicated background by using seeded region growing. AEU Int J Electron Commun 2012; 66(9): 767-71.
[http://dx.doi.org/10.1016/j.aeue.2012.01.011]
[http://dx.doi.org/10.1016/j.aeue.2012.01.011]
[5]
Canny J. A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 1986; 8(6): 679-98.
[http://dx.doi.org/10.1109/TPAMI.1986.4767851] [PMID: 21869365]
[http://dx.doi.org/10.1109/TPAMI.1986.4767851] [PMID: 21869365]
[6]
Kang Y, Engelke K, Kalender WA. A new accurate and precise 3-D segmentation method for skeletal structures in volumetric CT data. IEEE Trans Med Imaging 2003; 22(5): 586-98.
[http://dx.doi.org/10.1109/TMI.2003.812265] [PMID: 12846428]
[http://dx.doi.org/10.1109/TMI.2003.812265] [PMID: 12846428]
[7]
Lim PH, Bagci U, Bai L. Introducing Willmore flow into level set segmentation of spinal vertebrae. IEEE Trans Biomed Eng 2013; 60(1): 115-22.
[http://dx.doi.org/10.1109/TBME.2012.2225833] [PMID: 23144025]
[http://dx.doi.org/10.1109/TBME.2012.2225833] [PMID: 23144025]
[8]
Huang J, Jian F, Wu H, Li H. An improved level set method for vertebra CT image segmentation. Biomed Eng Online 2013; 12(1): 48.
[http://dx.doi.org/10.1186/1475-925X-12-48] [PMID: 23714300]
[http://dx.doi.org/10.1186/1475-925X-12-48] [PMID: 23714300]
[9]
Tang LM, Tian XQ, Huang DR, Wang XF. Image segmentation model combined with FCMS and variational level set. Acta Automatica Sinica 2014; 40(6): 1233-48.
[10]
Kass M, Witkin A, Terzopoulos D. Snakes: active contour models. Int J Comput Vis 1988; 1(4): 321-31.
[http://dx.doi.org/10.1007/BF00133570]
[http://dx.doi.org/10.1007/BF00133570]
[11]
Chan TF, Vese LA. Active contours without edges. IEEE Trans Image Process 2001; 10(2): 266-77.
[http://dx.doi.org/10.1109/83.902291] [PMID: 18249617]
[http://dx.doi.org/10.1109/83.902291] [PMID: 18249617]
[12]
Li CM, Kao CY, Gore JC, Ding ZH. Implicit active contours driven by local binarytting energy.IEEE Conf Comp Vis Patt Recogn. 2007; 2007: pp. 1-7.
[13]
Klinder T, Ostermann J, Ehm M, Franz A, Kneser R, Lorenz C. Automated model-based vertebra detection, identification, and segmentation in CT images. Med Image Anal 2009; 13(3): 471-82.
[http://dx.doi.org/10.1016/j.media.2009.02.004] [PMID: 19285910]
[http://dx.doi.org/10.1016/j.media.2009.02.004] [PMID: 19285910]
[14]
Huang SH, Chu YH, Lai SH, Novak CL. Learning-based vertebra detection and iterative normalized-cut segmentation for spinal MRI. IEEE Trans Med Imaging 2009; 28(10): 1595-605.
[http://dx.doi.org/10.1109/TMI.2009.2023362] [PMID: 19783497]
[http://dx.doi.org/10.1109/TMI.2009.2023362] [PMID: 19783497]
[15]
Roberts MG, Cootes TF, Adams JE. Segmentation of lumbar vertebrae via part-based graphs and active appearance models. Lect Notes Comput Sci 2009; 5762: 1017-24.
[http://dx.doi.org/10.1007/978-3-642-04271-3_123]
[http://dx.doi.org/10.1007/978-3-642-04271-3_123]
[16]
Chen K, Li B, Tian LF. A segmentation algorithm of pulmonary nodules using active contour model based on fuzzy speed function. Acta Automatica Sinica 2013; 39(8): 1257-64.
[http://dx.doi.org/10.3724/SP.J.1004.2013.01257]
[http://dx.doi.org/10.3724/SP.J.1004.2013.01257]
[17]
Rastgarpour M, Shanbehzadeh J, Soltanian-Zadeh H. A hybrid method based on fuzzy clustering and local region-based level set for segmentation of inhomogeneous medical images. J Med Syst 2014; 38(8): 68.
[http://dx.doi.org/10.1007/s10916-014-0068-3] [PMID: 24957392]
[http://dx.doi.org/10.1007/s10916-014-0068-3] [PMID: 24957392]
[18]
Krinidis S, Chatzis V. A robust fuzzy local information C-Means clustering algorithm. IEEE Trans Image Process 2010; 19(5): 1328-37.
[http://dx.doi.org/10.1109/TIP.2010.2040763] [PMID: 20089475]
[http://dx.doi.org/10.1109/TIP.2010.2040763] [PMID: 20089475]
[19]
Tang LM, Wang HK, Chen ZH, Huang DR. Image fuzzy clustering segmentation based on variational level set. J Softw 2014; 25(7): 1570-82.
[20]
Thieu QT, Luong M, Rocchisani JM, Sirakov NM, Viennet E. Efficient segmentation with the convex local-global fuzzy Gaussian distribution active contour for medical applications. Ann Math Artif Intell 2015; 75(1): 249-66.
[http://dx.doi.org/10.1007/s10472-014-9413-y]
[http://dx.doi.org/10.1007/s10472-014-9413-y]
[21]
Sun WY, Dong EQ, Cao ZL, Zheng Q. A robust local segmentation method based on fuzzy-energy based active contour. Acta Automatica Sinica 2017; 43(4): 611-21.
[22]
Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal 2017; 42: 60-88.
[http://dx.doi.org/10.1016/j.media.2017.07.005] [PMID: 28778026 ]
[http://dx.doi.org/10.1016/j.media.2017.07.005] [PMID: 28778026 ]
[23]
Adhish P, Kersten P, Christian I, François L, Erik D, Mads N.Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. Medical image computing and computer-assisted intervention In:
. Nagoya, Japan; Berlin Heidelberg: Springer-Verlag 2013; pp. 22-6.
[24]
Jonathan L, Evan S, Trevor D. Fully convolutional networks for semantic segmentation.The IEEE conference on Computer Vision and Pattern Recognition (CVPR). 2015 Jun 08-12; Boston, Massachusetts. USA .
[25]
Kooi T, Litjens G, van Ginneken B, et al. Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal 2017; 35(35): 303-12.
[http://dx.doi.org/10.1016/j.media.2016.07.007] [PMID: 27497072]
[http://dx.doi.org/10.1016/j.media.2016.07.007] [PMID: 27497072]
[26]
Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. IEEE Trans Pattern Anal Mach Intell 2018; 40(4): 834-48.
[http://dx.doi.org/10.1109/TPAMI.2017.2699184] [PMID: 28463186]
[http://dx.doi.org/10.1109/TPAMI.2017.2699184] [PMID: 28463186]
[27]
Lu F, Wu F, Hu P, Peng Z, Kong D. Automatic 3D liver location and segmentation via convolutional neural network and graph cut. Int J CARS 2017; 12(2): 171-82.
[http://dx.doi.org/10.1007/s11548-016-1467-3] [PMID: 27604760]
[http://dx.doi.org/10.1007/s11548-016-1467-3] [PMID: 27604760]
[28]
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention In: Munich, Germany; Switzerland: Springer International Publishing. 2015; pp. 5-9.
[29]
Suzani A, Seitel A, Liu Y, Fels S, Rohling RN, Abolmaesumi P. Fast automatic vertebrae detection and localization in pathological CT Scans - A deep learning approach. Medical image computing and computer-assisted intervention. In: Munich, Germany; Switzerland: Springer International Publishing. 2015; pp. 5-9.
[30]
Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. Computer Vision and Pattern Recognition 2016.
[31]
Milletari F, Navab N, Ahmadi S-A. V-net: fully convolutional neural networks for volumetric medical image segmentation. Fourth international conference on 3D Vision (3DV). In: . Stanford, USA; USA: IEEE Xplore 2016; pp. 25-8.
[32]
Nikolas L, Bram VG, Ivana I. Iterative convolutional neural networks for automatic vertebra identification and segmentation in CT images. Medical Imaging 2018; p. 105741057408.
[33]
Nie D, Wang L, Trullo R, et al. Segmentation of craniomaxillofacial bony structures from MRI with a 3D deep-learning based cascade framework. Mach Learn Med Imaging 2017; 10541: 266-73.
[http://dx.doi.org/10.1007/978-3-319-67389-9_31] [PMID: 29417097]
[http://dx.doi.org/10.1007/978-3-319-67389-9_31] [PMID: 29417097]
[34]
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition.Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE 2015; pp. 770-8.
[35]
Yeong TK. Contrast enhancement using brightness preserving bi-histogram equalization. IEEE Trans Consum Electron 1997; 43(1): 1-8.
[http://dx.doi.org/10.1109/30.580378]
[http://dx.doi.org/10.1109/30.580378]
[36]
Pizer SM, Amburn EP, Austin JD. Adaptive histogram equalization and its variations. Comput Vis Graph Image Process 1987; 39(3): 355-68.
[http://dx.doi.org/10.1016/S0734-189X(87)80186-X]
[http://dx.doi.org/10.1016/S0734-189X(87)80186-X]
[37]
Ali MR. Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for real-time image enhancement. Journal of VLSI signal processing systems for signal 2004; 38(1): 35-44.
[38]
Kai MH, Xian GZ, Shao QR, Jian S. Deep residual learning for image recognition The IEEE conference on Computer Vision and Pattern Recognition. CVPR: Las Vegas, USA 2016.
[39]
Yang QJ, Evan S, Jeff D. Caffe: convolutional architecture for fast feature embedding. Proceedings of the 22nd ACM international conference on multimedia. Florida, USA. 2014.
[40]
Yao J, Burns JE, Forsberg D, et al. A multi-center milestone study of clinical vertebral CT segmentation. Comput Med Imaging Graph 2016; 49: 16-28.
[http://dx.doi.org/10.1016/j.compmedimag.2015.12.006] [PMID: 26878138]
[http://dx.doi.org/10.1016/j.compmedimag.2015.12.006] [PMID: 26878138]
[41]
Forsberg D. Atlas-Based registration for accurate segmentation of thoracic and lumbar vertebrae in CT data Recent Advances in computational methods and clinical applications for spine imagingIn: . Munich, Germany; Switzerland: Springer International Publishing 2015; pp. 5-9.
[http://dx.doi.org/10.1007/978-3-319-14148-0_5]
[http://dx.doi.org/10.1007/978-3-319-14148-0_5]
Article Metrics
15
3