Classification of brain tumor types using multiclass kernel-based Hellinger decision method for HD-Tree and HD-Forest

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Currently, the radiologist needs to distinguish the medical imaging with their multiple classes. In this paper, we work on several steps: segmented ROI, feature extraction of ROI and classification. In this work, we proposed a multiclass kernel based Hellinger decision method HD-Tree and HD-Forest for the classification of brain tumor classes with respect to classification time and accuracy. The calculated features like patient symptoms, centroid, shape, etc. are used in the classification scheme. Total 97 MRI brain tumor images (Astrocytoma (22), Ganglioglioma (6), Glioblastoma (23), Epidermoid (3), Mixed Glioma (5) and Meningnet (41)) were used for the experiment. The Experimental result shows that kernel-based Hellinger HD-Tree was found to be 96.50 % of accuracy and HD-Forest was found to be 99.9%. In this paper, we compare our proposed method LA-SVM method. LA-SVM was found to be 96% of accuracy. We can see that HD-forest gives the best accuracy result.


  • Keywords


    MRI Brain Tumor; Feature Extraction; Classification; Kernel HD-Tree; Kernel HD-Forest; SVM.

  • References


      [1] David A, Cieslak, Ryan Hoens T, Nitesh V, Chawla W (2012), Philip Kegelmeyer. Hellinger distance decision trees are robust and skew-insensitive. Springer Knowl Disc, 24:136–158 https://doi.org/10.1007/s10618-011-0222-1.

      [2] Liew AWC and Yan H (2006), Current methods in the automatic tissue segmentation of 3D magnetic resonance brain images. Current Med Imaging Rev, 91–103, pp.2 (1).

      [3] Pham DL, Xu C, and Prince JL (2002), Current methods in medical image segmentation. Annu Rev Biomed Eng 2:315–337 https://doi.org/10.1146/annurev.bioeng.2.1.315.

      [4] Dahshan El. A. EI, Hosny T and Salem A M (2010), Hybrid Intelligent Techniques for MRI Brain Image Classification. Elsevier Digital Signal Processing, vol.20, pp. 433–441. https://doi.org/10.1016/j.dsp.2009.07.002.

      [5] Zacharaki El, Wang S, Chawla S, Yoo D S, Wolf R, Melhem E R, and Davatzikos C (2009), Classification of Brain Tumor Type and Grade using MRI Texture in a Machine Learning Technique.’ Magn. Reson. Med, vol.62, pp.1609-1618. https://doi.org/10.1002/mrm.22147.

      [6] Praveen G B and Agarwal A (2015), Hybrid Approach for Brain Tumor Detection and Classification in Magnetic Resonance Images. International Conference on Communication, Control and Intelligent Systems (CCIS), 2015, 978-1-4673-7541-2. https://doi.org/10.1109/CCIntelS.2015.7437900.

      [7] Kong J, Wang J, Yinghu Li Y, Zhang Lu Z and Zhang B (2006), A novel approach for segmentation of MRI brain image. IEEE Melecon, Benalmádena (Málaga), Spain.

      [8] Marroquin J L, Vemuri B C, Botello S, Calderon F, and Fernandez-Bouzas A (2002), An accurate and efficient bayesian method for automatic segmentation of Brain MRI. IEEE Transactions on medical imaging, pp. 21(8).

      [9] Clarke L P, Velthuizen R P, Camacho M A, Heine J J, Vaidyanathan M L, Hall O, Thatcher R W and Silbiger M L (1995), MRI segmentation: methods and applications. Magnetic Resonance Imaging, 343-368, pp.13 (3).

      [10] Singh N and Jindal A (2012), A Survey of different types of Characterization Technique in Ultra- sonograms of the Thyroid Nodules. International journal of computer science and informatics, 2231-5292, pp. 1(4).

      [11] Singh N and Choudhary N (2014), A Review of Brain Tumor Segmentation and Detection Techniques through MRI. International Journal of Computer Applications, 0975 – 8887, pp. 103(7).

      [12] Singh N and Choudhary N (2017), Automatic localization and level set based energy minimization for MRI brain tumor. IEEE International Conference on Computer, Communications and Electronics (Comptelix), 978-1-5090-4708-6. https://doi.org/10.1109/COMPTELIX.2017.8003951.

      [13] Georgiardis P, Cavouras D, Kalatzis I, Daskalakis A, Kagadi D C, Malamas M, Nikifordis G, Solomou E (2007), Non-linear least square feature transformations for improving the performance of probabilistic neural networks in classifying human brain tumors on MRI. Lecture Notes on Computer Science, pp. 239-47. https://doi.org/10.1007/978-3-540-74484-9_21.

      [14] Georgiardis P, Cavouras D, Kalatzis I, Daskalakis A, Kagadi D C, Malamas M, Nikifordis G, Solomou E (2008), Improving brain tumor characterization on MRI by probabilistic neural networks on non-linear transformation of textural features. Comput Meth Prog Bio., vol. 89, pp.24-32. https://doi.org/10.1016/j.cmpb.2007.10.007.

      [15] Lyon R J, Brooke J M, Knowles J D and Stoppers B W (2014), Hellinger Distance Trees for Imbalanced Streams. 22nd International Conference on Pattern Recognition. https://doi.org/10.1109/ICPR.2014.344.

      [16] Chaplot S, Patnaik L M and Jagannathan N R (2006), Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network. Biomedical Signal Processing and Control, vol. 1, pp. 86–92. https://doi.org/10.1016/j.bspc.2006.05.002.

      [17] Hoens T R, Qian Qi, Nitesh Chawla V, and Zhi-Hua Zhou (2012), Building Decision Trees for the Multi-class Imbalance Problem. Springer-Verlag Berlin Heidelberg, pp.122-134 https://doi.org/10.1007/978-3-642-30217-6_11.

      [18] Song Y, Zhang C, Lee J, Wang F, Xiang Z, and Zhang D (2009), Semi-supervised discriminative classification with application to tumorous tissues segmentation of MR brain images. Pattern Anal Application, 99–115, pp. 12. https://doi.org/10.1007/s10044-008-0104-3.

      [19] Zhang Y, Dong Z, Wu L, Wang S (2011), A Hybrid Method for MRI Brain Image Classification. Expert system with applications, vol.38, pp.10049-10053. https://doi.org/10.1016/j.eswa.2011.02.012.


 

View

Download

Article ID: 8571
 
DOI: 10.14419/ijet.v7i1.8571




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