Artificial Neural Network based Classification of Brain Tumor from MRI using FCM and Bounding Box Method

DOI : 10.17577/IJERTV4IS051084

Download Full-Text PDF Cite this Publication

Text Only Version

Artificial Neural Network based Classification of Brain Tumor from MRI using FCM and Bounding Box Method

Meghana N1 , 1M Tech Student , Dept of ECE, SJBIT

Uttarahalli Main Road, Kengeri,Bangalore-60, Karnataka

Dr Rekha K R2

2 Professor,

Dept of ECE SJBIT, Bangalore Uttarahalli Main Road, Kengeri, Bangalore-60,


Abstract- Brain tumor segmentation consists of separating the different tumor tissues or active tumor, from normal brain tisssues.The detection of edema is done simultaneously with tumor segmentation, as the knowledge of the extent of edema is important for diagnosis, planning and treatment. Magnetic resonance image technique (MRI) is used in medical diagnosis.MRI Scanners uses magnetic fields to form images of brain tumor for its detection. Accurate analysis for location and size of tumor is approached.FCM and bounding box based segmentation of brain images is prescribed. Bounding box is a fast segmentation technique that includes symmetry to enclose a tumours or edema by a bounding box within an axial brain MR image.segmented tumor is classified using Artificial neural network training

Keywords: MRI, Fuzzy C Means, Bounding box, Bhattacharya co-efficient,Histogram co-relation,Neural network training.


Accurate estimation of tumor size and its area is important for diagnosis e.g., treatment planning and therapy evaluation. A tumour can be defined as a mass which grows without any control of normal forces. Magnetic resonance (MR) imaging and computer tomography (CT) scanning of the brain are the two most common tests undertaken to confirm the presence of brain tumour and to identify its location for selected specialist treatment options. Real time diagnosis of tumours by using more reliable algorithms has been the main focus of the latest developments in medical imaging. The detection of brain tumour in MR images and CT scan images has been an active research area. The tumor may be primary or secondary. If the part of the tumor is spread to another place and grown as its own then it is known as secondary. Normally the brain tumor affects CSF (Cerebral Spinal Fluid).It causes Strokes.


    The fuzzy logic is a way to processing the data by giving the partial membership value to each pixel in the image. The membership value of the fuzzy set ranges from 0 to 1. Fuzzy clustering is basically a multi valued logic that allows intermediate values i.e., member of one fuzzy Set can also be member of other fuzzy sets in the same image. Apriority specification of the number of clusters. Most of the fuzzy models work well only for hyper intensity (fully enhanced) tumors and exhibit poor performance on detecting non-enhanced tumors. This is because these fuzzy models typically use thresholding techniques or morphological operations (erosion or dilation) as pre- or post-processing leading to the border enhancing or non-enhancing tumors having very few bright pixels


    1. A novel fast Fuzzy C means clustering technique for segmentation of human brain MRI.

      This approach calculates cluster centre in each iteration by new formula. A type of averaging among cluster centres is applied in each iteration step however; membership function is a fuzzy coefficient.

    2. Comparative study of brain tumour segmentation techniques for extracting brain tumour from MRI.

      Bounding box segmentation technique is used. Segmentation is based on histogram analysis and Bhattacharya co-effiecents.

    3. Brain tumour detection using K-means and Fuzzy C means Clustering algorithm.

      This algorithm clusters data by iteratively computing mean intensity for each class and segmentating the image by classifying each pixel in the class with closest mean.

    4. Neural network based brain tumor detection using MR images

      The boundary detection problem is formulated as an optimization process that seeks the boundary points to minimize an energy functional based on an active contour model


    Our aim is to achieve a high accuracy in discriminating the type of tumor through a combination of several techniques for image segmentation, feature extraction and classification. The proposed technique has the potential of assisting clinical diagnosis. We present an automatic, fast, and approximate segmentation technique that avoids these problems by locating a bounding box i. e., an axis- parallel rectangle, around the tumor or edema on an MR slice. We can then use this bounding box to answer subsequent queries that ask about tumor position and size

    Proposed Block Diagram


    Fcm allows one set of data to belong to 2 or more clusters.FCM is introduced by Dunn and later extended by Bezdek.It is an iterative clustering method that produces an optimal C partition by minimizing the weighted within group.

    The objective function is an optimizing function that calculates weighted within group sum of squared error.

    Bounding box

    The geometrical axis of symmetry of the skull is sufficient for our BB method to localize brain tumor or edema accurately, and finding the geometrical axis of symmetry is easier than finding the actual axis of symmetry of the skull. The novelty of the FBB segmentation technique lies in a proposed score function that locates the bounding boxes. The score function is based on

    Bhattacharya coefficient of gray scale intensity histograms. We prove that under reasonable assumptions, this score function admits a very fast linear time search technique to locate the bounding boxes

    Classification using ANN

    An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons) working in unison to solve specific problems.


    The proposed work is implemented on MATLAB 7.11.0(R2010b).

      1. GUI for Brain tumor detection using neural network

      2. Bounding box segmentation for trained images

      3. Quiery Image for testing

      4. Bounding box segmentation

    (d) Segmented area and class

    Area Calculation is made by the simple calculation of knowing the properties of image.[11] Mostly the image has 256*256 pixels. Area of an image is the total number of the pixels present in the area which can be calculated in the length units by multiplying the number of pixels with the dimension of one pixel.

    Image, I = 255=0 255=0[f(0) + f(1)]

    Pixels = Width (W) X Height (H) = 256 X 256 f (0) = white pixel (digit 0)

    f (l) = black pixel (digit 1)

    No_ of_ white pixel P = 255=0 255=0[f(0)] Where,

    P = number of white pixel (width*height)


For accurate diagnosis of brain tumour patients, proper segmentation method is required to be used for MR images to carry out an improved diagnosis and treatment. There are different types of tumours available. They may be as mass in brain or malignant over the brain. Suppose if it is a mass then K- means algorithm is enough to extract it from the brain cells. FBB is a novel fast segmentation technique that uses symmetry to enclose an anomaly (typically, tumours or edema) by a bounding box within an axial brain MR image.ANN is used for classification of the segmented area.The networks were ategorized into feed-forward neural networks and Back propagation neural Network. The purpose is to develop tools for discriminating malignant tumors from benign ones assisting decision making in clinical diagnosis.


  1. M.C.Jobin Christ,Ramanan Subramanian, R.Thirumalvalavan,A.VigneshAutomatic Brain Tumor Segmentation by Variational Minimax Optimization Technique International Journal of Innovative Research in Science,Vol 3,Issue 2 Feb 2014.

  2. Turkish Journal of Fuzzy Systems (eISSN: 13091190)An Official Journal of Turkish Fuzzy Systems Association Vol.4, No.1, pp. 34- 47, 2013

  3. Rachana Rana, H.S. Bhadauria, Annapurna Singh Comparative study of brain tumour segmentation techniques for extracting brain tumor from MRI Proc. of the Second Intl. Conf. on Advances in Electronics, Electrical and Computer Engineering — EEC 2013[2]

  4. Kadam D. B., Gade S. S., M. D. Uplane andR. K. Prasad Neural network based brain tumor detection using MR images International Journal of Computer Science and Communication Vol. 2, No. 2, July-December 2011, pp. 325-331.

  5. Roopali R.Laddha, S.A.Ladhake A review of on Brain tumour detection using segmentation and threshold operationsInternational Journal of Computer Science and Information Technologies, Vol. 5 (1) , 2014, 607-611.

  6. Yinghua Lu, Tighui Ma, Changhong Yin, Xiaoyu Xie, Wei TianImplementation of the Fuzzy C-means clustering Algorithm in Meterological dataInternational Journal of Database Theory and application vol 6.No 6(2013).pp.1-18.

  7. J.selvakumar , A.Lakshmi, T.Arivoli, Brain Tumor Segmentation and Its Area Calculation in Brain MR images using K-Mean Clustering and Fuzzy C-Mean Algorithm , IEEE-International Conference On Advances In Engineering, Science And Management (ICAESM – 2012) March 30, 31, 2012.

  8. Sudipta Roy, Samir K.Bandyopadhyay, Detection and Quantification of Brain Tumour from MRI of Brain and its Symmetric Analysis, IJICTR, Volume 2 No. 6, June 2012.

  9. Krishna Kant Singh, Akansha Singh,A Study Of Image Segmentation Algorithms For Different Types Of Images, IJCSI International Journal of Computer Science Issues, Vol. 7, Issue 5,September 2010 [10]R.B.Dubey,ShantaramVasikarla,Evaluation of Three Methods for MRI Brain Tumor Segmentation, 2011 Eighth International

Conference on IT.

  1. Ms. Sonali. B. Maind, Ms. Priyanka Wankar Research Paper on Basic of Artificial Neural Network International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169 Volume: 2 Issue: 1.

  2. Ue-Pyng Wena,1, Kuen-Ming Lan a,1, Hsu-Shih Shih A review of Hopfield neural networks for solving mathematical programming problems European Journal of Operational Research 2008 Elsevier B.V.

  3. Anjum Hayat Gondal, Muhammad Naeem Ahmed KhanA review of fully automated techniques for brain tumor detection for MR Images I.J.Modern Education and Computer Science, 2013, 2, 55- 61

  4. Pham D., Xu C., and Prince J.,(2000), A Survey of Current Methods in Medical Image Segmentation, Annual Review of Biometrical Engineering, vol. 2, no. 3, pp. 315-337.

  5. Yong Yang and Shuying Huang, (2007), Image Segmentation By Fuzzy C- Means Clustering Algorithm With A Novel Penalty Term, Computing and Informatics, vol. 26, pp. 17-31

  6. Tolias Y. A. and Pans S. M., (1998), On Applying Spatial Constraints in Fuzzy Image Clustering Using a Fuzzy Rule- Based System, IEEE Signal Processing Letters Vol. 5, pp. 245-247.

  7. GauriP.Anandgaonkar,Ganesh.S.SableDetection and identification of Brain tumour in Brain MR images using Fuzzy C means segmentation International Journal of Advanced Research in Computer and Communication Engineering Vol. 2, Issue 10, October 2013.

Leave a Reply