Automatic segmentation of vertebrae in 3D CT images using adaptive fast 3D pulse coupled neural networks
- 80 Downloads
Two systems are presented for segmentation of vertebrae in a 3D computed tomography (CT) image. The first method extracts seven features from each voxel and uses a multi-layer perceptron neural network (MLPNN) to classify the voxel as vertebrae or background. In the second method, the segmentation is completed in two steps: first, a newly developed adaptive pulse coupled neural network (APCNN) directly applied to a given image segments vertebrae, then the result is refined using a median filter. In the developed APCNN, the values for the user-defined parameters of the pulse coupled neural networks (PCNN) are adaptively adjusted for each image individually, instead of using one value for all images as in conventional PCNN. The performance of both systems in terms of Dice index (DI) was evaluated and compared against the state-of-the-art segmentation methods using seventeen clinical and standard CT images. Overall, both systems demonstrated statistically similar and promising performance with average DI > 95%. Compared to existing PCNN-based segmentation algorithms, the accuracy of the proposed APCNN improved by 29.3% on average. The developed APCNN-based system is more accurate than MLPNN-based system and existing PCNN-based algorithms in segmentation of vertebrae with blurred and weak boundaries and in the images contaminated by salt- and- pepper noise. In terms of computation time, the APCNN-based system is 16 times faster than the MLPNN-based system. Consequently, the presented APCNN-based algorithm is both accurate and fast and could be used in clinical environment for segmentation of vertebrae in 3D CT images.
KeywordsFeature extraction Multi-layer perceptron Pulse-coupled neural networks Vertebrae segmentation
We would also like to thank the staffs of Medical Imaging center of Namazi hospital and Taba medical imaging center, Shiraz, Iran and Spine CT image site  for sharing the medical images used in this research and assisting with analysis of this images. The authors wish to thank Mr. H. Argasi at the Research Consultation Center (RCC) of Shiraz University of Medical Sciences for his invaluable assistance in editing this manuscript.
This study was funded by Shiraz University of Medical Sciences (Grant # 93-01-01-8772).
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
For the part of this study that we used data (image) of patients, all the procedures performed in this work involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed consent was obtained from all individual participants included in the study whom their 3D vertebrae CT images acquired in Medical Imaging center of Namazi hospital and Taba medical imaging center, Shiraz, Iran.
- 1.Roberts MG, Cootes TF, Adams JE Vertebral shape: automatic measurement with dynamically sequenced active appearance models. In: International conference on medical image computing and computer-assisted intervention. Springer, p. 733–740Google Scholar
- 2.Gupta G, Kaur T (2012) Denoising of computed tomography images using curvelet transformation with log Gabor filter. Int J Sci Eng Res 3:1000–1003Google Scholar
- 4.Suzani A, Rasoulian A, Fels S, Rohling RN, Abolmaesumi P (2014) Semi-automatic segmentation of vertebral bodies in volumetric MR images using a statistical shape + pose model. SPIE Med Imaging 2014:90360Google Scholar
- 8.Mirzaalian H, Wels M, Heimann T, Kelm BM, Suehling M (2013) Fast and robust 3D vertebra segmentation using statistical shape models. In: Engineering in Medicine and Biology Society (EMBC), 2013 35th annual international conference of the IEEE. IEEE, pp 3379–3382Google Scholar
- 11.Li Y, Liang W, Tan J, Zhang Y (2015) A novel automatically initialized level set approach based on region correlation for lumbar vertebrae CT image segmentation. In 2015 IEEE international symposium on medical measurements and applications (MeMeA), IEEE, pp 291–296Google Scholar
- 13.Haykin SO (2008) Neural networks and learning machines, 3 edn. Pearson, New YorkGoogle Scholar
- 14.Lindblad T, Kinser JM, Lindblad T, Kinser JM (2005) Image processing using pulse-coupled neural networks. Springer, BerlinGoogle Scholar
- 20.Chang Q, Shi J, Xiao Z (2009) A new 3D segmentation algorithm based on 3D PCNN for lung CT slices. In: BMEI. IEEE, pp 1–5Google Scholar
- 27.Yi-de M, Qing L, Zhi-bai Q (2004) Automated image segmentation using improved PCNN model based on cross-entropy. In: Proceedings of 2004 international symposium on intelligent multimedia, video and speech processing, 2004. IEEE, pp 743–746Google Scholar
- 30.Tuceryan M, Jain AK (1993) Texture analysis. Handb Pattern Recognit Comput Vis 2:207–248Google Scholar
- 31.Baraldi A, Parmiggiani F (1995) An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters. Geosci Remote Sens 33:283–304Google Scholar
- 34.Chang Q, Shi J, Xiao Z (2009) A new 3D segmentation algorithm based on 3D PCNN for lung CT slices. In: Biomedical engineering and informatics 2009. BMEI09 2nd international conference. IEEE, pp 1–5Google Scholar
- 36.Spine CT image dataset. [Internet]. http://research.microsoft.com/project/medicalimageanalysis