Classification of Brain Cancer Detection by using Magnetic Resonance Imaging

DOI : 10.17577/IJERTV3IS20996

Download Full-Text PDF Cite this Publication

Text Only Version

Classification of Brain Cancer Detection by using Magnetic Resonance Imaging

Vishal S. Shirsat

Department of computer science & Information Technology Dr.Babasaheb Ambedkar Marathwada University Aurangabad, Maharashtra India

Seema S. Kawathekar

Department of computer science & Information Technology Dr.Babasaheb Ambedkar Marathwada University Aurangabad, Maharashtra India

Abstract Human system is made up of many organs, of all brain is the first and the leading controller of the human system. Overload cells growing in an uncontrolled manner in brain is called as brain tumor. MRI brain tumor image can be evaluated only by expert physicians. In medical image processing brain tumor detection is one of the challenging tasks. Sometime MRI brain images corrupted by some noise. In this paper we specially focus on detecting tumor from brain MRI images. Proposed algorithm performs pre-processing operations on brain MRI images to remove noise from MRI images with the help of median filter, logarithmic transform and then by applying segmentation for detecting tumor from brain MRI image by using thresholding. Using thresholding techniques extraction of the tumor takes place and then calculates the tumor area. An online database is used and for result analysis used receiver operating characteristic ROC curve, and this algorithm achieves 80% with respect to sensitivity and specificity 20%. The proposed algorithm is very useful to gives more information about the tumor which is very helpful to the doctor for subjective analysis.

KeywordsMagnetic Resonance Imaging (MRI), Logarithimic Transform (LT), Receiver operating characteristic (ROC).

  1. INTRODUCTION

    In Medical Diagnostic, Magnetic Resonance Imaging plays a major role. Magnetic resonance imaging (MRI) is a test that uses a magnetic field and pulses of radio wave energy to make pictures of organs and structures inside the body. In many cases MRI gives different information about structures in the body than can be seen with an X-ray, ultrasound, or computed tomography (CT) scan [1, 2]. Brain tumor detection approach in medical magnetic resonance imaging is very important in order to perform Diagnostic image analysis. Due to the involvement of various kinds of abnormalities, pathology, radiologists perception and image analysis at diagnosis stage, manual segmentation of brain tumor from MR image seems to be a difficult and time consuming task. Brain tumor is the most commonly occurring spite among human beings, so study of brain tumor is important [1]. In this paper our proposed method is an image segmentation method to identify or detect tumor from the brain cancer image using magnetic resonance imaging.

  2. METHODOLOGY

    Our proposed methodology is a four-step process the block based approach is used to analyze MRI brain tumor images. In

    this approach, the brain tumor is detected. The involved methodology is given below,

    Thresholding

    Pre-processing

    MRI image

    Detected tumor area

    Output

    Fig. 1. Purposed Method

    For detecting the tumor we have used image processing techniques, like for enhancement of brain MRI images here is used logarithmic transformation function, for highlighting the brain tumor then threshold function is used and for detecting the tumor watershed Segmentation is used. After completing this procedures 80 % Results are found.

  3. PREPROCESSING

    In preprocessing, after getting input MRI image, noise is found in the image .To remove noise and to detect exact location of tumor, thresholding technique is used. Here remove the noise from image and enhanced their quality by using image processing techniques.

    1. logarithmic transform

      In biomedical image processing of images face some different problems such as darkness & blurring in images, etc. To solve this problem logarithmic transform gives more extended values of dark pixels and convert values for a bright pixels. It compresses the dynamic range of images with large variations in pixel values [1, 2, and 7]. Logarithmic transform can be calculated by using this equation.

      s = c log (1 + r)………. (I)

      Where c is a constant, r is pixel value of image. And it is assumed that r 0. This transformation uses a narrow range of low-level gray scale intensities into a wider range of output values. And similarly record the wide range of high-level grey scale intensities into a narrow range of high level output values. The opposite of this applies for inverse-log transform.

    2. Thresholding

    Thresholding is nothing but a conversion of binary image into gray scale image. It is also a very useful method for detecting the object of the image. Thresholding techniques [6, 8, and 10] are image segmentations techniques based on image-space regions. The fundamental principle of thresholding techniques is based on the characteristics of the image. In brightness threshold, all the pixels brighter than a specified brightness level are taken as 1 and the rest are left 0. In this way we got a new binary image is formed with useful objects image as 1 and unwanted as background 0. Sufficient contrast on objects and background is necessary to do the thresholding. The simplest property that pixels in a region can share is intensity. A natural way to separate such regions is through thresholding, to light and dark- regions. Thresholding creates binary images from grey level ones by turning all pixels below some threshold to zero and all pixels above that threshold to one. Thresholding is the transformation of an input image to an output binary image gas represented by the next formula, where g(x, y) is a threshold version of f(x, y) at some global threshold.

  4. EXPERIMENTAL RESULTS

    The proposed Algorithm was tested with different MRI Brain cancer images. The proposed Algorithm was tested with the brain having different intensity, shape and size. Proposed method was successful to competently extract the tumor part from the brain tumor images. The method was tested using MATLAB 2012a. Experimental results for the MRI brain cancer kinds of images are shown below.

    Fig. 2. Example of a Thresholding

    Fig.3.Example of Thresholding

    TABLE I. RECEIVER OPERATING CHARACTERISTIC

    Sr no

    Receiver Operating Characteristic

    Image name

    Ground truth

    TP

    TN

    FP

    FN

    1

    000001

    Tumor present

    Yes

    2

    000002

    Tumor present

    Yes

    3

    000003

    Tumor present

    yes

    4

    000004

    Tumor present

    Yes

    5

    000005

    Tumor present

    Yes

    6

    000006

    Tumor present

    Yes

    7

    000007

    Tumor present

    No

    Yes

    8

    000008/p>

    Tumor present

    yes

    9

    000009

    Tumor present

    yes

    10

    000010

    Tumor present

    Yes

    Fig.4. Receiver Operating Characteristic

    Fig.4. Separated tumor from MRI image

    Fig.5. Separated tumor from MRI image

  5. CONCLUSION & FUTURE WORK

In this purposed work different medical images, like MRI brain & MRI brain cancer images are taken for detecting tumor. The Proposed algorithm is developed with the help of mat lab and image processing techniques. For result analysis receiver operating characteristic curve (ROC) is used and this algorithm achieves sensitivity equal to 80 % and specificity equal to 23 % and accuracy is 0.9902. ROC curve which is helpful for the classification of the research work and also it gives the accuracy. In future we will take a large database and try to give more accuracy as compare to this one which will work on any type MRI brain tumor & with objective analysis.

REFERENCES

  1. Debnath Bhattacharyya, Tai-honn kim, brain tumor detection using MRI image analysis, in UCMA, 2011, Part II, CCIS 151, paper 307- 314, 2011.

  2. Shrija madhu, T.M.Sirishal, Detection of brain tumor using thresholding and morphological operators volume no.3 (2013), issue no.09 (September), 2013.

  3. Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins: Digital Image Processing using MATLAB, Chapter 10, pp. 378 425, Pearson Education, 2004.

  4. W. Malina, S. Ablameyko, W. Pawlak. Fundamental Methods of Digital Image Processing. (In Polish), 2002.

  5. E. A. Savakis. Adaptive Document Image Thresholding Using Foreground and Background clustering published in Proceeding of International Conference on Image Processing ICIP, 98.

  6. L. Spirkovsk. A Summary of Image Segmentation Techniques, Ames Research Center, Moffett Field, California, 1993.

  7. Vishal Shirsath, Dr.Seema kawathakar, Nagsen Bansod, Vijay Shirale,Noise Removal & Tumor detection Technique for MRI in Medical imaging CMS 2013

  8. K.Selvanayaki, Dr. M. Karnan: CAD System for Automatic Detection of Brain Tumor through Magnetic Resonance Image-A Review.

  9. Suita Dhariwal, Comparative Analysis of Various image enhancement techniques sept 20.

  10. Paul Bao* and Lei Zhang, Noise Reduction for Magnetic Resonance Images via Adaptive Multiscale Products Thresholding , IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 22, NO. 9,

    SEPTEMBER 2003

  11. D. W. McRobbie, E. A. Moore, M. J. Graves, M. R. Prince, and MRI: From picture to proton. 2nd. Ed. New York: Cambridge University. 2007

  12. Haack.Eetal., Magnetic Resonance Imaging, Physical Principles and Sequence Design, Wieley-Liss, New York, 1999.

  13. Resonance Imaging "Magnetic Resonance Imaging". Websters Online Dictionary. Retrieved 25 April 2012.

  14. C. Lakshmi Devasena, M. Hemalatha Noise Removal in Magnetic Resonance Images using Hybrid KSL Filtering Technique International Journal of Computer Applications (0975 8887) Volume 27 No.8, August 2011.

  15. Zolqernine Othman, habibollah haron, Mohammad Rafiq Abdul Kadir,Comparison of Canny and Sobel Edge Detection in MRI images2008

  16. Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing. 3nd. Ed. New Jersey: Pearson Prentice Hall. 2008.

  17. Mohamed Ali and David Clausi (2001), Using the Canny Edge Detector for Feature Extraction an] Enhancement of Remote Sensing Images, IEEE, pp 2298-2300.

  18. Bhausaheb Shinde, Dnyandeo Mhaske, A.R. Dani Study of Image Processing, Enhancement and Restoration IJCSI, Vol. 8, Issue 6, No 3, November 2011.

  19. Tirpude NN, Welekar RR Effect Of Global Thresholding onTumor-

    Bearing Brain Mri Images 3 March

  20. M. Young, The Technical Writers Handbook. Mill Valley, CA: University Science, 1989.

Leave a Reply