A Novel Feature Extraction Method for The Detection of CMBs

Authors

  • Berakhah. F. Stanley  Assistant Professor, Arunachala College of Engineering for Women, Vellichanthai, Tamil Nadu, India
  • Dr. S. Wilfred Franklin  Professor, C.S.I Institute of Technology, Thovalai, Tamil Nadu, India
  • R. Jeen Retna Kumar  Assistant Professor, Bethlahem Institute of Engineering, Karungal, Tamil Nadu, India

Keywords:

Abstract

CMBs are deposits found in the brains of elderly people and stroke victims. This can lead to dementia as well as a variety of other issues with everyday activities like remembering, driving, and so on. In this paper, an effective feature extraction technique to detect cerebral microbleeds (CMB) has been proposed. In the feature extraction stage, weber local descriptor is applied which extracts two components. In these components Gray-level Co-occurance Matrix (GLCM) and Histogram of Oriented Gradient (HOG) are applied. Thus, two sets of features are extracted. In the classification stage, Artificial Neural Network is used to identify the CMB and non- CMBs areas. This method gives the sensitivity of 83.3%, specificity of 76.9% and an accuracy of 80%. The result of this technique is free from human errors.

References

  1. Charidimou A, Krishnan A, Werring DJ,Jager HR, “Cerebral microbleeds: a guide to detection and clinical relevance in different disease settings”, Neuro-radiology, 2013; 55;  655-74.
  2. Balafar, Mohammad. (2012), “Review of Noise Reducing Algorithms for Brain MRI Images”. IJTPE. 4. 54-59.
  3. Y. Zhang, Z. Dong, L. Wu and S. Wang, “A hybrid method for MRI brain image classification”, Expert Syst. Appl. 38 (8) (2011) 10049-10053. doi:10.1016/ j.eswa.2011.02.012. URL ttps://doi.org/10.1016/j.eswa.2011.02.012
  4. Y. Zhang, Z. Dong, S. Wang, G. Ji and J. Yang, “Preclinical diagnosis of magnetic resonance (MR) brain images via discrete wavelet packet transform with tsallis entropy and generalized eigenvalue proximal support vector machine(GEPSVM)”, Entropy 17 (4) (2015) 1795-1813. doi:10.3390/e17041795. URL http://www.mdpi.com/1099-4300/17/4/1795
  5. E. A. El-Dahshan, T. Hosny and A. M. Salem, Hybrid intelligent techniques for MRI brain images classification, Digital Signal Processing 20 (2) (2010) 433-441. doi:10.1016/j.dsp.2009.07.002. URL https://doi.org/10.1016/j.dsp.2009.07.002
  6. D.R.Nayak, R.Dashand, B.Majhi, “Brain MR image classification using two-dimensional discrete wavelet transform and ada boost with random forests”, Neurocomput. 177 (C) (2016) 188-197. doi:10.1016/j.neucom.2015.11. 034. URL https://doi.org/10.1016/j.neucom.2015.11.034
  7. Mohammed Khalil, Habib Ayad, Abdellah Adib, “Performance evaluation of feature extraction techniques in MR-Brain image classification system”, Procedia Computer Science, Volume 127, 2018, Pages 218-225, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2018.01.117.
  8. H. J. Kuijf, J. de Bresser, G. J. Biessels, M. A. Viergever and K. L. Vincken, "Detecting cerebral microbleeds in 7.0 T MR images using the radial symmetry transform," 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Chicago, IL, 2011, pp. 758-761.

International Journal of Scientific Research in Science and Technology

Downloads

Published

2021-04-10

Issue

Volume 9, Issue 1, March-April-2021

Section

Research Articles

License

Copyright (c) IJSRST

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Berakhah. F. Stanley, Dr. S. Wilfred Franklin, R. Jeen Retna Kumar, " A Novel Feature Extraction Method for The Detection of CMBs, International Journal of Scientific Research in Science and Technology(IJSRST), Online ISSN : 2395-602X, Print ISSN : 2395-6011, Volume 9, Issue 1, pp.749-759, March-April-2021.