Main Article Content

Abstract

The brain is the anterior most part of the central nervous system. The cranium, a bony box in the skull protects it. Virtually every activity or thought of ours is controlled by our brain. So, it’s very dangerous when the proper functioning of the brain is hindered. Brain tumor is one such disease which if not detected early and treated accordingly, can prove fatal. Structure of the brain is quite complex and hence it is very difficult to detect the abnormalities in early stages. In our paper we will be giving an overview of the various techniques used for brain tumor detection and how SIFT overcomes their limitations. The techniques discussed include biopsy, manual segmentation, mathematical morphology & wavelet transform, artificial neural network and finally SIFT (Scale Invariant Feature Transform). Biopsy is a surgical method which needs to be performed by highly skilled professionals. The rest other methods use MRI images and thus are non-invasive. SIFT technique which we are using in our project gives good accuracy, is cost effective and most importantly is invariant to translation, scale, rotation, affine transform, change in illumination, etc.

Keywords

MRI images SIFT tumor k-means k-NN DoG.

Article Details

How to Cite
Pani, A., Shende, P., Dhumal, M., Sangle, K., & Shiravale, S. (2015). ADVANTAGES OF USING SIFT FOR BRAIN TUMOR DETECTION. International Journal of Students’ Research in Technology & Management, 1(3), 327–338. Retrieved from https://mgesjournals.com/ijsrtm/article/view/75

References

  1. Leyla Zhuhadar, IEEE Member and Gopi Chand Nutakki, IEEE Member, University of
  2. Louisville, Louisville, USA: Hybrid Appearance Based Disease Recognition of Human
  3. Brains, International Conference on Information Visualisation, 2012.
  4. J. Samuel, M. Dong, J. Hua, and E. M. Haacke: Wayne State University, Detroit, MI, United
  5. States: Brain Tumor Detection Using Scale Invariant Feature Transform, 2011.
  6. Dipali M. Joshi, Dr.N. K. Rana, V. M. Misra: Classification of Brain Cancer Using Artificial
  7. Neural Network, International Conference on Electronic Computer Technology (ICECT
  8. Ahmed Kharrat, Mohamed Ben Messaoud, Nacéra Benamrane, Mohamed Abid: Detection of
  9. Brain Tumor in Medical Images, International Conference on Signals, Circuits and Systems,
  10. Q. Li, J. Ye, M. Li, and C. Kambhamettu, Adaptive appearance based face recognition, IEEE
  11. International Conference on Tools with Artificial Intelligence (ICTAI), 2006.
  12. D. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, IJCV, Vol. 60(2), 91-
  13. , 2004.
  14. Shen, L.L. and Bai, L. and Fairhurst, M. Gabor wavelets and general discriminant analysis for
  15. face identification and verification Image and Vision Computing.
  16. Gonzalez, R.C. Richard, E.w; “Digital Image Processing,â€(2004), II Indian Edition, Pearson
  17. Education, New Delhi, India.
  18. M. Sonka, J. M. Fitzpatrick, Handbook of Medical Imaging- Processing and Analysis. I.N.
  19. IEEE Trans. Med. Imaging ( 2001).
  20. “Automated segmentation of MR images of brain tumorsâ€, Kaus MR, Warfield SK, Nabavi A,
  21. Black PM, Jolesz FA, Kikinis R. RSNA, Radiology. 2001 Feb;218(2):586-91.
  22. Zhu, Y. and Tan, T. and Wang, Y. Biometric personal identification based on iris patterns
  23. Published by the IEEE Computer Society, 2000.
  24. [12] P. Soille, "Morphological Image Analysis, Principals and applicationâ€, Springer,