i-manager Publications

Support Vector Machine for Classification of Spinal Cord Tumor

Geetha R.*, Mohan J.**

* ** Department of Electronics and Communication Engineering, SRM Valliammai Engineering College, SRM Nagar, Tamil Nadu.

Periodicity:January - March'2020
DOI : https://doi.org/10.26634/jip.7.1.16741

Abstract

This paper is a development of an algorithm to classify the spinal cord tumor in MRI images based on medical image processing. Most of researches involve deep learning algorithms to solve classification problem and is approached to detect tumor. From these considerations, approach of SVM for spinal cord tumor classification has been proposed. The method is improving the accuracy, sensitivity, specificity for the given spinal cord image. In pre-processing method, the spinal cord image is denoised using NLM filter, After image is denoised, Convolutional Neural Network(CNN) has been applied to extract the features from the segmented spinal cord image, which is obtained the texture details and used to identified the matched image. Support Vector Machine (SVM) is used for image classification. Finally, our proposed system is applied with a total of 500 images, including four kinds of spinal cord tumor images and our research experiment provides maximum value of the average accuracy, sensitivity, specificity are 98.1 (Astrocytomas), 98.9 (Astrocytomas), 97.17 (Hemangioblastomas) respectively. Minimum values of the accuracy, sensitivity, specificity are 93.8 (Ependymomas), 95.9 (Hemangioblastomas), 95.04 (Meningiomas) respectively.

Keywords

Spinal Cord Tumor, Types of Spinal Cord Tumor, Classification, Convolutional Neural Network, Support Vector Machine.

How to Cite this Article?

Geetha, R., and Mohan, J. (2020). Support Vector Machine for Classification of Spinal Cord Tumor. i-manager's Journal on Image Processing , 7(1), 40-44. https://doi.org/10.26634/jip.7.1.16741

References

(1). Bampis, C. G., Bovik, A. C., Markey, M. K., & Webb, K. M. (2016, March). Segmentation and extraction of the spinal canal in sagittal MR images. In 2016 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) (pp. 5-8). IEEE. https://doi.org/10.1109/SSIAI.2016.7459161

(2). Chmelik, J., Jakubicek, R., Walek, P., Jan, J., Ourednicek, P., Lambert, L., Amadori, E., & Gavelli, G. (2018). Deep convolutional neural network-based segmentation and classification of difficult to define metastatic spinal lesions in 3D CT data. Medical Image Analysis, 49, 76-88. https://doi.org/10.1016/j.media.2018. 07.008

(3). Eidelson, S. G. (2019). Spinal Tumors Center: Spineuniverse. Retrieved from https://www.SpineUniverse .com/ Conditions/Spinal-Tumors

(4). Li, Y., Zhou, W., Lv, G., Luo, G., Zhu, Y., & Liu, J. (2018, October). Classification of bone tumor on ct images using deep convolutional neural network. In International Conference on Artificial Neural Networks (pp. 127-136). Springer, Cham. https://doi.org/10.1007/978-3-030-01421- 6_13

(5). Mahmud, A. A., Karim, A. H. M. Z., Mou, F. A., & Rashedur, S. (2016). Spine tumor detection using MRI. International Journal of Biomedical Materials Research, 4(3), 35-42. https://doi.org/10.11648/j.ijbmr.20160403.15

(6). Major, D., Hladůvka, J., Schulze, F., & Bühler, K. (2013). Automated landmarking and labeling of fully and partially scanned spinal columns in CT images. Medical Image Analysis, 17(8), 1151-1163. https://doi.org/10.1016/j.me dia.2013.07.005

(7). Toghraee, M., Toghraee, M., Silvoster, M. L., & Rad, F. (2018). Design CNN on bone spine segmention to methods image processing. Journal of Electronics and Communication Systems, 3(2), 1-12.

	North Americas,UK, Middle East,Europe		India	Rest of world
	USD	EUR	INR	USD-ROW
Pdf	35	35	200	20
Online	35	35	200	15
Pdf & Online	35	35	400	25

Support Vector Machine for Classification of Spinal Cord Tumor

Abstract

Keywords

How to Cite this Article?

References

If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Options for accessing this content: