MULTI CLASS SEGMENTATION OF SPINAL VERTEBRAE USING IMPROVED REGION EXTRACTION TECHNIQUE IN IMAGE PROCESSING
Keywords:
Region Extraction, Wiener Filter, Fuzzy C-Means Clustering, Cluster Formation, Edge DetectionAbstract
Image Segmentation is generally used to separate the objects from the background, and it has proved to be a powerful tool in Bio-medical imaging for the diagnosis of various images. Generally, Segmentation involves dividing the image into various constituent parts or objects by performing various algorithms to segment the desired part from the image. The Magnetic Resonance (MR) Image is used for representing the soft tissue, organs, and also three-dimensional visualization inside of the human body. The proposed system involves the multi-class segmentation of spinal vertebrae where with magnetic resonance (MR) image plays a significant role in various spinal disease diagnoses and treatments of spine disorders. The Existing fully convolutional network-based methods has a disadvantage that it fails to work for the different spinal structures. Hence, the proposed model includes the Fuzzy C- means Clustering for the Cluster Formation Algorithm to increase the efficiency of the system and the optimized image is obtained for the diagnosis. The cluster formed will be extracted by the Mean GGN Growing Properties which helps to get the other data points for the evaluation, and finally, the Fractional Ridge Edge Detection Technique detects the edges from the extracted cluster image. The Proposed model uses the Weiner Filter to remove the noise in the 2D input MR Image and the Region Based Segmentation will extract only the affected cells from the input image even when the cells are scattered. The Simulation is done in MATLAB and performs around 400 iterations for the Edge Detection Technique and the Area, Perimeter , Centroid and Diameter are calculator for the cluster in order to get the accuracy is increased to 95%.
References
D. Forsberg, “Atlas-based segmentation of the thoracic and lumbar vertebrae,” in Recent Advances in Computational Methods and Clinical Applications for Spine Imaging. Springer, 2015, pp. 215–220.
C. Wang and D. Forsberg, “Segmentation of intervertebral discs in 3d MRI data using multi-atlas based registration,” in Lecture Notes in Computer Science. Springer International Publishing, 2016, pp. 107– 116.
P. H. Lim, U. Bagci, and L. Bai, “Introducing willmore flow into level set segmentation of spinal vertebrae,” IEEE Transactions on Biomedical Engineering, vol. 60, no. 1, pp. 115–122, 2012.
A. Neubert, J. Fripp, C. Engstrom, R. Schwarz, L. Lauer, O. Salvado, and S. Crozier, “Automated detection, 3d segmentation and analysis of high resolution spine mr images using statistical shape models,” Physics in Medicine & Biology, vol. 57, no. 24, p. 8357, 2012.
S. Kadoury, H. Labelle, and N. Paragios, “Spine segmentation in medical images using manifold embeddings and higher-order mrfs,” IEEE transactions on medical imaging, vol. 32, no. 7, pp. 1227–1238, 2013.
M. W. Law, K. Tay, A. Leung, G. J. Garvin, and S. Li, “Intervertebral disc segmentation in mr images using anisotropic oriented flux,” Medical image analysis, vol. 17, no. 1, pp. 43–61, 2013.
B. Ibragimov, R. Korez, B. Likar, F. Pernus, L. Xing, and T. Vr- ˇ tovec, “Segmentation of pathological structures by landmark-assisted deformable models,” IEEE transactions on medical imaging, vol. 36, no. 7, pp. 1457–1469, 2017.
C. Chen, D. Belavy, W. Yu, C. Chu, G. Armbrecht, M. Bansmann, D. Felsenberg, and G. Zheng, “Localization and segmentation of 3d intervertebral discs in mr images by data driven estimation,” IEEE transactions on medical imaging, vol. 34, no. 8, pp. 1719–1729, 2015.
H. Chen, Q. Dou, X. Wang, J. Qin, J. C. Cheng, and P.-A. Heng, “3d fully convolutional networks for intervertebral disc localization and segmentation,” in International Conference on Medical Imaging and Augmented Reality. Springer, 2016, pp. 375–382.
R. Janssens, G. Zeng, and G. Zheng, “Fully automatic segmentation of lumbar vertebrae from ct images using cascaded 3d fully convolutional networks,” in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). IEEE, 2018, pp. 893–897.
X. Li, Q. Dou, H. Chen, C.-W. Fu, X. Qi, D. L. Belavy, G. Armbrecht, ` D. Felsenberg, G. Zheng, and P.-A. Heng, “3d multi-scale fcn with random modality voxel dropout learning for intervertebral disc localization and segmentation from multi-modality mr images,” Medical image analysis, vol. 45, pp. 41–54, 2018.
A. Sekuboyina, A. Valentinitsch, J. S. Kirschke, and B. H. Menze, “A localisation-segmentation approach for multi-label annotation of lumbar vertebrae using deep nets,” arXiv preprint arXiv:1703.04347, 2017.
N. Lessmann, B. van Ginneken, P. A. de Jong, and I. Isgum, “Iterative fully convolutional neural networks for automatic vertebra segmentation,” 2018.
O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention. Springer, 2015, pp. 234–241.
L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoderdecoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 801–818.
Z. Han, B. Wei, A. Mercado, S. Leung, and S. Li, “Spine-gan: Semantic segmentation of multiple spinal structures,” Medical image analysis, vol. 50, pp. 23–35, 2018.
O. C¸ ic¸ek, A. Abdulkadir, S. S. Lienkamp, T. Brox, and O. Ronneberger, ¨ “3d u-net: learning dense volumetric segmentation from sparse annotation,” in International conference on medical image computing and computer-assisted intervention. Springer, 2016, pp. 424–432.
