Call for Paper - August 2022 Edition
IJCA solicits original research papers for the August 2022 Edition. Last date of manuscript submission is July 20, 2022. Read More

Automatic Classification of MR Brain Tumor Images using Decision Tree

IJCA Special Issue on International Conference on Electronics, Communication and Information systems
© 2012 by IJCA Journal
ICECI - Number 1
Year of Publication: 2012
Hema Rajini. N
Narmatha. T
Bhavani. R

Hema Rajini.n, Narmatha.t and Bhavani.r. Article: Automatic Classification of MR Brain Tumor Images using Decision Tree. IJCA Special Issue on International Conference on Electronics, Communication and Information systems ICECI(1):10-13, November 2012. Full text available. BibTeX

	author = {Hema Rajini.n and Narmatha.t and Bhavani.r},
	title = {Article: Automatic Classification of MR Brain Tumor Images using Decision Tree},
	journal = {IJCA Special Issue on International Conference on Electronics, Communication and Information systems},
	year = {2012},
	volume = {ICECI},
	number = {1},
	pages = {10-13},
	month = {November},
	note = {Full text available}


A tumor classification system has been designed and developed. It is used to classify five different types of tumors such as glioblastoma multiforme, astrocytoma, metastatic, glioma and pituitary macro. The magnetic resonance feature images used for the tumor classification consist of T1-weighted images with contrast for each axial slice through the head. The magnetic resonance imaging has become a widely used method of high quality medical imaging, especially in brain imaging where the soft-tissue contrast and non invasiveness is a clear advantage. The proposed method has three stages. They are pre-processing, feature extraction and classification. In the first stage, the noise is removed using a wiener filter. In the second stage, six texture features are extracted using gray level co-occurrence matrix. The features extracted are angular second moment, contrast, inverse difference moment, entrophy, correlation and variance. Finally, a decision tree classifier is used to classify the type of tumor image. The extracted features are compared with the stored features in the knowledge base to classify the type of tumors. Thus, the proposed system has been evaluated on a dataset of 21 patients. Then the system was found efficient in classification with a success of 98%.


  • Ricci, P. E. and Dungan, D. H. 2001. Imaging of low and intermediate-grade gliomas. SEMRADONC, 11(2), 103-112.
  • Armstrong, T. S. , Cohen, M. Z. , Weinbrg, J. and Gilbert, M. R. 2004. Imaging techniques in neuro oncology. SEMONCNUR, 20(4): 231-239.
  • Prasad, P. V. 2006. MRI: Methods and Biologic Applications, Humana Press Inc.
  • Gibbs, P, Buckley, D. L, and Blackband, S. J. 1996. Tumour volume determination from MR images by morphological segmentation. Phys Med Biol, 41(11): 2437-2446.
  • Letteboer, M. M. J, Olsen, O. F and Dam, E. B. 2004. Segmentation of tumors in magnetic resonance brain images using an interactive multiscale watershed algorithm. Acad Radiol, 11: 1125-1138.
  • Droske, M, Meyer, B and Rumpf, M. 2005. An adaptive level set method for interactive segmentation of in tracranial tumors. Neuro Res, 27(4): 363-370.
  • Fletcher-Heath, L. M, Hall, L. O and Goldgof, D. B. 2001. Automatic segmentation of non-enhancing brain tumors in magnetic resonance images. Artif Intell Med, 21(1-3): 43-63.
  • Zou, K. H, Wells, W. M and Kikinis, R. 2004. Three validation metrics for automated probabilistic image segmentation of brain tumours. Stat Med, 23(8): 1259-1282.
  • Dou, W, Ruan, S, Chen, Y, Bloyet, D and Constans, J. M. 2007. A framework of fuzzy information fusion for segmentation of brain tumor tissues on MR images. Image and Vision Computing, 25: 164–171.
  • K. M. Iftekharuddin, M. Islam, J. Shaik, C. Parra, and R. Ogg, "Automatic brain-tumor detection in MRI: Methodology and statistical validation," SPIE Medical Imaging, Vol. 5747, pp. 2012-2022, February 2005.
  • K. M. Iftekharuddin, W. Jia, and R. Marsh, "A fractal analysis of tumor in brain MR images," Mack Vision Appl. , Vol. 13, pp. 352-362, 2003.
  • K. M. Iftekharuddin, C. Parra, "Multiresolution-fractal feature extraction and tumor detection: Analytical modeling and implementation," Proc. Of SPIE 47th Annual Meeting in Wavelets, vol. 5207, pp. 801-812, San Diego, CA, August 2003.
  • Anirban, M and Ujjwal, M. 2011. A multiobjective approach to MR brain image segmentation. Applied Soft Computing, 11: 872–880.
  • Cheng, H. D, Shan, J, Ju, W, Guo, Y and Zhang, L. 2010. Automated breast cancer detection and classification using ultrasound images: A survey. Pattern Recognition, 43: 299–317.
  • Ahmed. K, Karim. G, Mohamed. B. M, Nacera. B, Mohamed. A. 2010. A hybrid approach for automatic classification of brain MRI using genetic algorithm and support vector machine. Leonardo Journal of Sciences Issue 17: 71-82.
  • Baskaran. R, Deivamani. M, Kannan. A, 2004. "A multi agent approach for texture based classification and retrieval (MATBCR) using binary decision tree. " International journal of computing and information sciences, Vol. 2, No. 1, 13-22.
  • Dipali M. Joshi, Rana. N. K, Misra. V. M, 2010. "Classification of Brain Cancer Using Artificial Neural Network", IEEE, 112-116.
  • Fazel Zarandi. M. H, Zarinbal. M, Izadi. M, 2011. "Systematic image processing for diagnosing brain tumors: A Type-II fuzzy expert system approach" Applied Soft Computing, 285-294.
  • Fritz Albregtsen, "Statistical Texture Measures Computed from Gray Level Coocurrence Matrices," Image Processing Laboratory, Department of Informatics, University of Oslo, pp. 1-14, November 5, 2008.