Segmenting and classifying MRI images for brain tumors using CNN

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Gliomas are one of the most prevalent and aggressive form of brain tumours in the world. Patient's usually go on to live a very short life after the initial diagnosis. Therefore, it is crucial to successfully and quickly outline a method for diagnosing the same in it's very earliest stages.Magnetic Resonance Imaging, or MRI as it is more frequently called is a noninvasive method of imaging parts of human anatomy. MRI's utilise robust fields of magnetism, along with waves that have frequencies corresponding to the radio waves in the spectrum to develop precise pictures to get a sense of the happenings inside the human body. The current, most widely used method of diagnosis for brain gliomas involves an oncologist or radiologist reading the MRI image and using his knowledge and experience regarding the same to reach a diagnosis. However, this manual method of diagnosis is very tedious and has been prone to errors in the past. Therefore, it essential to develop an automatic method for the same.Most of the techniques used currently for segmenting brain tumours were initially developed for other diseases, the most common use among them being the separation of white matter lesions. Most of the current methodologies can be broadly categorised into two families- 1.General Probabilistic Methods- Probabilistic methods are a remarkable method to establish the validity of combinatorial entities with distinct characteristics. Although the basis of their existence lies in probability, they are not bounded by it and can be used to solve and evaluate theorems across different branches of Mathematics.2.Discriminative Approaches- They are also sometimes referred to as Conditional Models. We utilise CNN's for faster and accurate processing of the data.

     

     


  • Keywords


    MRI’s; CNN; Contrast; Contours; ANN.

  • References


      [1] S. Bauer et al., “A survey of MRI-based medical image analysis for brain tumor studies,” Phys. Med. Biol., vol. 58, no. 13, pp. 97–129, 2013.

      [2] D. N. Louis et al., “The 2007 who classification of tumors of the central nervous system,” Acta Neuropathologica, vol. 114, no. 2, pp. 97–109, 2007.

      [3] E. G. Van Meir et al., “Exciting new advances in neuro-oncology: The avenue to a cure for malignant glioma,” CA, Cancer J. Clinicians, vol. 60, no. 3, pp. 166–193, 2010.

      [4] G. Tabatabai et al., “Molecular diagnostics of gliomas: The clinical perspective,” Acta Neuropathologica, vol. 120, no. 5, pp. 585–592, 2010.

      [5] B. Menze et al., “The multimodal brain tumor image segmentation benchmark (BRATS),” IEEE Trans. Med. Imag., vol. 34, no. 10, pp. 1993–2024, Oct. 2015.

      [6] N. J. Tustison et al., “N4ITK: Improved n3 bias correction,” IEEE Trans. Med. Imag., vol. 29, no. 6, pp. 1310–1320, Jun. 2010.

      [7] L. G. Nyúl, J. K. Udupa, and X. Zhang, “New variants of a method of MRI scale standardization,” IEEE Trans. Med. Imag., vol. 19, no. 2, pp. 143–150, Feb. 2000.

      [8] M. Prastawa et al., “A brain tumor segmentation framework based on outlier detection,” Med. Image Anal., vol. 8, no. 3, pp. 275–283, 2004.

      [9] B. H. Menze et al., “A generative model for brain tumor segmentation in multi-modal images,” in Medical Image Computing and Comput. - Assisted Intervention-MICCAI 2010. New York: Springer, 2010, pp. 151–159.

      [10] A. Gooya et al., “GLISTR: Glioma image segmentation and registration,” IEEE Trans. Med. Imag., vol. 31, no. 10, pp. 1941–1954, Oct. 2012.

      [11] D. Kwon et al., “Combining generative models for multifocal glioma segmentation and registration,” in Medical Image Computing and Comput.-Assisted Intervention-MICCAI 2014. New York: Springer, 2014, pp. 763–770.

      [12] S. Bauer, L.-P. Nolte, and M. Reyes, “Fully automatic segmentation of brain tumor images using support vector machine classification in combination with hierarchical conditional random field regularization,” in Medical Image Computing and Comput.-Assisted Intervention-MICCAI 2011. New York: Springer, 2011, pp. 354–361.

      [13] C.-H. Lee et al., “Segmenting brain tumors using pseudo-conditional random fields,” in Medical Image Computing and Comput.-Assisted Intervention-MICCAI 2008. New York: Springer, 2008, pp. 359–366.

      [14] R. Meier et al., “A hybrid model for multimodal brain tumor segmentation,” in Proc. NCI-MICCAI BRATS, 2013, pp. 31–37.

      [15] R. Meier et al., “Appearance-and context-sensitive features for brain tumor segmentation,” in MICCAI Brain Tumor Segmentation Challenge (BraTS), 2014, pp. 20–26.

      [16] T. Chan and L. Vese, “Active contours without edges,” IEEE Trans. Image Process. vol. 10, no. 2, pp. 266–277, Feb. 2001.

      [17] Minimizaion of region-scalable fitting energy for image segmentation. IEEE Trans. Image Processing, vol. 17 (10), pp.1940-1949, 2008.by Li chunming etc.

      [18] M.N. Ahmed ET. al. "A Modified Fuzzy C-Means Algorithm for Bias Field estimation and Segmentation of MRI Data" 2002, IEEE Transactions on medical imaging.


 

View

Download

Article ID: 18545
 
DOI: 10.14419/ijet.v7i3.29.18545




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.