|
Vol: 58(72) No: 1 / March 2013 Bones Contour Segmentation in Radiograph Images Cosmin Cernazanu-Glavan Department of Computer Science, Politehnica University of Timisoara, Faculty of Automatic Control and Computer Science, Timisoara, Romania, phone: (+40) 256-403281, e-mail: cosmin.cernazanu@cs.upt.ro Stefan Holban Department of Computer Science, Politehnica University of Timisoara, Faculty of Automatic Control and Computer Science, Timisoara, Romania, e-mail: stefan.holban@cs.upt.ro Keywords: neural network, convolution, segmentation, medical images Abstract A necessary step for any automatic method of diagnose is the demarcation of the bone tissue from an X-ray image. Consequently, in this article we will present a new method of segmentation and demarcation of the bone tissue using a Convolution Neural Network (CNN). This type of network is intensively used in the field of image processing because it provides high adaptability towards the unclear images and the noises present in them. As the X-ray images have large dimensions (high resolution), in order to improve the training time, only the interest areas have been cut from the initial image. For these areas, a CNN was used as classifying pixel for affiliating each pixel in the X-ray image to one of the two classes {bone, non-bone}. Compared to the traditional methods of segmentation, the method presented by us obtained the best results reaching a minimum value for the evaluation metrics used i.e. pixel error. References [1] J. Schmid, N. Magnenat-Thalmann, “MRI Bone Segmentation using Deformable Models and Shape Priors”, Med Image Comput Comput Assist Interv., vol. 11, pp. 119-26, 2008. [2] L. I. Wang, M. Greenspan, R. Ellis, “Validation of bone segmentation and improved 3-D registration using contour coherency in CT data”, IEEE Transactions on Medical Imaging, vol. 25, no. 3, pp.324-334, March 2006. [3] R. C. Gonzalez, R. E. Woods, “Digital Image Processing”, Prentice Hall, 2001. [4] A. Goshtasby, D. A. Turner, “Segmentation of cardiac cine MR images for extraction of right and left ventricular chambers”, IEEE Transactions on Medical Imaging, vol. 14, no. 1, pp. 56-64, 1995. [5] M. Bomans, K.-H. Hohne, U. Tiede, M. Riemer, “3-D segmentation of MR images of the head for 3-D display”, IEEE Transactions on Medical Imaging, vol. 9, no. 2, pp. 177-183, 1990. [6] C. Harris, M. Stephens, “A combined corner and edge detector”, in Proceedings of 4th ALVEY Vision Conference, pp. 147-151, 1988. [7] J. Canny, “A computational approach to edge detection”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp. 679-698, November 1986. [8] J. Feng, W.-C. Lin, C.-T. Chen, “Epicardial boundary detection using fuzzy reasoning”, Medical Imaging, IEEE Transactions on, vol.10, no.2, pp.187-199, Jun. 1991. [9] M. S. Brown, M. F. McNitt-Gray, N. J. Mankovich, J. G. Goldin, J. Hiller, L. S. Wilson, D. R. Aberie, “Method for segmenting chest CT image data using an anatomical model: preliminary results”, IEEE Transactions on Medical Imaging, vol. 16, no. 6, pp. 828-839, 1997. [10] D. L. Toulson, J. F. Boyce, “Segmentation of MR image using neural nets”, Image and Vision Computing, vol. 10, pp. 324-328, 1992. [11] K. Fukushima, “Neocognitron: A self-organizing neural network for a mechanism of pattern recognition unaffected by shift in position”, Biological Cybernetics, 36 , 193-202, 1980. [12] Y. LeCun, L. Bottou, Y. Bengio and P. Haffner, “Gradient-Based Learning Applied to Document Recognition”, Proceedings of the IEEE, vol. 86(11), pp. 2278-2324, November 1998. [13] P. Y. Simard, D. Steinkraus, J. C. Platt, “Best practices for convolutional neural networks applied to visual document analysis”, In International Conference on Document Analysis and Recognition, pp. 958-963, 2003. [14] G. E. Hinton, S. Osindero, Y.-W. Teh, “A fast learning algorithm for deep belief nets”, Neural Computation, 2006. [15] Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle, “Greedy layerwise training of deep networks”, in Neural Information Processing Systems, 2007. [16] T. Serre, L. Wolf, T. Poggio, “Object recognition with features inspired by visual cortex”, in Proc. of Computer Vision and Pattern Recognition Conference, 2005. [17] D. Scherer, A. Muller, S. Behnke, “Evaluation of pooling operations in convolutional architectures for object recognition”, in International Conference on Artificial Neural Networks, 2010. [18] A. Krizhevsky, “Convolutional deep belief networks on CIFAR-10”, Technical report, University of Toronto, Aug. 2010. [19] C. Cernazanu, S. Holban, “X-ray image segmentation with convolution neural network”, in Proceedings of 32nd International Conference on Medical Informatics (ROMEDINF 2012), Timisoara, Romania, 2012. [20] J.M.S.Prewitt, “Object Enhancement and Extraction”, in B.S. Lipkin and A Rosenfeld eds. Picture Processing and Psychohistories, 1970. |