International Journal of All Research Education and Scientific Methods (IJARESM)

ISSN: 2455-6211, Volume 4, Issue 12, December- 2016

Review on Brain Tumour Detection using

Digital Image Processing
Shaifali Agarwal1, Shivangi Agarwal2
1,2
Member IEEE, CSE Department, Jaypee University Anupshahr (UP) India

ABSTRACT

Medical image processing is the most challenging and emerging field today. This paper describes the
methodology detection and extraction of brain tumour from patient’s MRI scan images of the brain. In
this paper,A method for segmentation of brain tumour has been developed on 2D-MRI data which allows
the identification of tumour issue with high accuracy and reproducibility compared to manual
techniques. This method incorporates with some noise removal functions, segmentation and
morphological operations which are the basic concepts of image processing. Detection and extraction of
tumour from MRI scan images of the brain is done by using MATLAB software. The aim of this work is
design an automated tool for brain tumour quantification using MRI image data sets.

Keywords: Brain tumour, grey scale imaging, MRI, MATLAB, morphology, noise removal, segmentation.

I. INTRODUCTION

Tumour is defined as the abnormal growth of the tissues .Epilepsy is a brain disorder in which clusters of never
cells, or neurons, In the brain sometimes signal abnormally. Neurons normally generate electrochemical
impulses that act another neurons, glands, and muscles to produce human thoughts, feelings and actions. And
behaviour or sometimes convulsions, muscle spasms and loss of consciousness [1-5].

In epilepsy, the normal pattern of neuronal activity becomes disturbed, causing strange sensations,
emotions,.Magnetic Resonance Imaging (MRI) is an advanced medical imaging technique used to produce high
quality images of the parts contained in the human body [6-12]. From these high-resolution images, we can
derive detailed anatomical information to examine human brain development and discover abnormalities. MRI
of T1 weighted, T2 weighted and PD(proton density)weighted images and are processed by a system which
integrates fuzzy based technique with multispectral analysis.

II. METHODOLOGY

The algorithm has two stages, first is the pre-processing of given MRI image[13-16] and after that segmentation
and then morphological operations.

Steps of algorithm are as following:-

1) Give MRI images of brain as input.

2) Convert it to Grey scale image.

3) Apply high pass filter for noise removal

4) Apply median filter to enhance the quality of image.

5) Compute threshold segmentation.

6) Compute watershed segmentation.

7) Compute morphological operation.

8) Finally output will be a tumour region.

33
International Journal of All Research Education and Scientific Methods (IJARESM)
ISSN: 2455-6211, Volume 4, Issue 12, December- 2016

Figure1. Proposed Framework

1. THE PROPOSED FRAMEWORK --The process flow of our proposed methodology may be shown as figure 1.
The First Section discusses how images are divided into regions using a block-based method.The second section
shows how each classified block is studied individually by calculating its multiple parameter values(5). In this
instance, The Multiparameter features refer to the following three specific features: the edges (E), Grey
Values(G), and local contrast (H) of the pixels in the block being-analysed.

2. INPUT IMAGE--The images we got fromMRI are the three types: axial Images, sagittalImages , Coronal
Images. The number of Images depends on the resolution of the movements of the MRI magnets.

III. PROCESSING

In processing the first step is to load the MRI image data set on to the MATLAB workspace and after loading
they will be processed. After this processing there are only three clips instead of 384 separate images,”i.e”
means “that is” one clip for axial images, one clip for sagittal images and one clip for coronal images.Axial,
Sagittal and coronal images were loaded and viewed in the MATLAB. After this, Axial, sagittal and coronal
movie clips were prepared and are shown in figure 2.

Figure2. Axial, sagittal and coronal images clips

Multi-Parameter Calculation

Classifying regions using their multi-parameter values makes the study of the regions of physiological and
pathological interest easier and more definable. The multi-parameter features refer to the following three
specific values for: the edges (E), Grey values (G), and local contrast (H) of the pixels.

Edges (E) Parameter

We use edge detection method to detect image edges (IE) is obtained by filtering an input image with two
convolution kernels concomitantly, one to detect changes in vertical contrast (Hx) and the other to detect
34
International Journal of All Research Education and Scientific Methods (IJARESM)
ISSN: 2455-6211, Volume 4, Issue 12, December- 2016

horizontal contrast (Hy), shown in equation(1). Image output (IE) is obtained by calculating the gradient
magnitude of each pixel, as shown inequation (2). Subsequently the edges parameter is calculated, whereby
E(r,x) is increased by one each time when IE(x,y)=’1’ in a supervised block, as shown in equations(3).

−1 0 1 −1 −2 −1
Hx- −2 0 2 ,Hr- 0 0 0 (1)
−1 0 1 1 2 1

IE(x,y)= Ix 2 (x, y) + Ir 2 (x, y) (2)

E(r,c) - (x,y)∊B (IEP==1) (3)

Grey (G) Parameter

The grey parameter (G) for each block of the brain is accumulated, and controlled by a binary image (IT) using
the GD value as a threshold, as shown in equation (6). GD value is calculated using the average pixel value (I avs)
of each image slice (S) for total image slices (T) of an image dataset,Shown in equation(4) and (5).

Iavs=1/65536 Ip(x,y) (4)

GD-1/T rs→0 Iavs (5)
G(r,c)= Ip x, y , ∀ IT x, y = 1(6)

Contrast (H)Parameter

Contrast (H) is often used to characterize the extent of variation in pixel intensity. We adopt the
minimum/maximum stretch algorithm for the 8-neighborhood connectivity, Where min H and max H present
the minimum and maximum intensity value of neighbourhood pixel C8(IH), as shown in equation (7). In the
previous studies, tumour cells are often associated with higher value of contrast (H) parameter. Hd is obtained by
totalling thecontrast of a supervised block, as shown in equation(8).

I x,y −min H
IH(x,y)= . *max H|H∊Cs(IH)(7)
maxH − min H

Hd(r,c)= (x,y)∈B IH(x, y)(8)

Segmentation Of Brain Tumour Using Region Of Interest (ROI) Command:-

As it has been seen from the above result that high density images have beenseparated from the MRI images
using Watershed Segmentation[17-20]. Here main aim is to segment the tumour from the MRI images. This can
be done by using the ROI command in MATLAB. After the application of the ROI command, the tumour may
be segmented. This can be achieved by executing the algorithm in MATLAB.All the calculation and techniques
can be summarized in following steps for the tumour detection:

A. Greyscale Imaging: MRI images are magnetic resonance scan of a patient taken with the help of a computer.
Generally a grey-scale looks like black and white images. The illusion of grey shading in a half-one image is
obtained by rendering the image as a grid of black of black dots on a white background (or vice-versa), with
sizes of individual dots determining the apparent lightness of the grey in their vicinity. In the case of transmitted
light (for example, the images on a computer display), the brightness level of the red (R), green (G)and blue (B)
components are each represented as a number from decimal 0 to 255, or binary 00000000 to 11111111. For
every pixel in a red-green-blue (RGB) grey-scale image, R=G=B.

The lightness of the grey is directly proportional to the numberrepresenting the brightness levels of the primary
colours. Black colour is representing by R=G=B=0 or R=G=B=00000000, and white is representing by
R=G=B=255 or R=G=B=11111111. Because there are 8 bits in the binary representation of the grey level, this
imaging method is called 8-bit grey-scale. The darkest possible shade is black, which is the total absence of
transmitted or reflected light. The lightest possible shade is white, the total transmission. So because of the
above reason first we convert our MRI image to be pre-processed in grey-scale image.

B. High Pass Filter: A high pass filter is method for sharpening methods. An image is sharpened when contrast
is enhanced between adjoining areas with variation in brightness and darkness. The kernel array of high pass
filter is designed to increase the brightness of the centre pixel relative to neighbouring pixels. The kernel array
contains a positive value surrounded by negative values.
35
International Journal of All Research Education and Scientific Methods (IJARESM)
ISSN: 2455-6211, Volume 4, Issue 12, December- 2016

C. Medical Filter: Medical filter is very widely used in digital image processing because, under certain
conditions, it preserves edges while removingnoise. The task of filtering is performed by the median filter by
use of window that is pattern of neighbours. The window pattern slides, entry by entry, over the entire signals.
The middle value of the window is decided by the median value of all the entries at a time.

D. Threshold Segmentation: This method is based on clip-level (or threshold value) to turn a grey-scale image
into a binary image by selecting a threshold value. Segmentation is the process of partitioning a digital image
into multiple segments, called super pixels. Image segmentation is typically used to located objects and
boundaries in images. By Threshold we assign a specific level to each pixel n image processing to the similarity
in visual characteristics.

E. Watershed Segmentation: A grey-scale may be seen as a topographic relief, where the grey level of a pixel
is interpreted as its altitude in the relief in the image processing, different watershed lines may be compute
Mayor’s flooding watershed algorithm[3] is used to compute the watershed segmentation. This algorithm works
on a grey scale image. During the successive flooding of the grey value relief, watersheds with adjacent
catchment basins are constructed. This flooding process is performed on the gradient image,i.e. the basins
should emerge along the edges. Normally this will lead to an over-segmentation of the image,especially for
noisy image material, e.g. medical CT data, either the image must be processed or the regions must be merged
on the basis of a similarity criterion afterwards.

MORPHOLOGICAL OPERATIONS

Morphological Operation is defined as the relative ordering of all the pixel value, not on the numerical values,
and therefore Are Especially suited for the processing of binary images. Morphological techniques probe an
image with a small shape and template called a structuring element. The structuring element ispositioned at all
possible locations in the image and it is compared with the corresponding neighbourhood of pixels. Some
operations Text whether the element “fits” within the neighbourhood, while other text whether it “hits” or
interests the neighbourhood. A morphological operation on a binary image creates a new binary image in which
pixels has a non-zero value only if the text is successful at that location in the input images.

RESULT AND CONCLUSION

The discussed methodology can be made clearer by considering an MRI image of tumour affected brain, shown
in figure3, and then performing all The operations in a sequence.

Figure3: MRI image of tumour affected brain

We get grey-scale image of the MRI images as shown in figure4.

Figure4: Grey Scale image

36
International Journal of All Research Education and Scientific Methods (IJARESM)
ISSN: 2455-6211, Volume 4, Issue 12, December- 2016

On performing high pass filtering on the greyscale image of figure 4 the HPF output is obtained as shown in
figure5

Figure5: HPF Output

There may be some noise in the greyscale image of the brain, after removing the noise the enhanced MRI image
is figure 6.

Figure6: Enhanced MRI image

The MRI greyscale images is converted into a binary image by applying threshold segmentation and given in a
figure 7.

Figure 7: Threshold Segmented Images of Input Images

For more accurate and precise result,watershed segmentation is done on the threshold segmented images and we
get the output image as shown in figure 8.

Figure 8 Watershed Segmented Image of Input Image

37
International Journal of All Research Education and Scientific Methods (IJARESM)
ISSN: 2455-6211, Volume 4, Issue 12, December- 2016

After the watershed segmentation the relative ordering of the pixel value of the image is done by morphological
operation and the output in each step is shown in figure 9

Figure 9: Morphological Operations

Finally on observing the difference in brightness or darkness in the MRI image, the brain tumour can be
detected as given in figure 10.

Figure 10: Final Extracted Brain Tumour From MRI Image.

FUTURE DIRECTION

In future this programme can be done more advanced so that major tumour can be classified according to its
type. Advancement in programming can help the segmentation completely automatic. By plotting the graph the
growth of the tumour can be analysed.

REFERENCES

[1]. W. Gonzalez , ”Digital Images Processing”, 2ndEg: Prentice Hall, Year of publication 2008, [378].
[2]. Dr. G. Padmavathi, Mr. M. Muthukumar and Mr. Suresh Kumar Thakur, “Non linear Image segmentation using
fuzzy c means clustering method with thresholding for underwater images”, IJCSI International Journal of Computer
Science Issues, Vol. 7, Issue 3,page No[ 9], May 2010
[3]. Abbasi S and Mokhtarian F (2001) Affine-similar shape retrieval: application to multiview 3-D object recognition.
IEEE Trans. Image processing. 10 (1), [31-139].
[4]. Abdel-HalimElamy and MaidongHu (2007) Mining brain tumors& their growth rates. IEEE Image Processing
Society Journal.pp: [872-875].
[5]. Bailet JW, Alan Lichtenstein, Ge Chen and Robert A. Mickel (1997) Inhibition of lymphocyte sfunction by head and
neck carcinoma cell line soluble factors. Arch Otolaryngol Head Neck Surg.123(8)[,855-862].
[6]. Bailet JW, Abemayor E, Jabour BA, Hawkins RA, Hoh CK and Ward PH (1992) Positron emission tomogarphy: a
new precise modality for detection of primary head and neck tumor and assessment of cervical adenopathy.
Laryngosope.102, [281- 288].
[7]. Black PM, Moriarty T and Alexander E (1997) Development and implementation of intraoperative magnetic
resonance imaging and its neurosurgical applications. Neurosurgery. 41(4), [831-845].

38
International Journal of All Research Education and Scientific Methods (IJARESM)
ISSN: 2455-6211, Volume 4, Issue 12, December- 2016

[8]. Bountris P, Farantatos E and Apostolou N (2005) Advanced image analysis tool development for the early stage
bronchial cancer detection. PWASET. 9, [151-156].
[9]. Deng Y, Manjunath BS, Kenney C, Moore MS and Shin H (2001) An efficient color representation for image
retrieval. IEEE Trans. Image Processing. 10 (1), [140-147].
[10]. Dewalle Vignion AS, Betrouni N and Makni N (2008) A new method based on both fuzzy set and possibility theories
for tumor volume segmentation on PET images. 30th Annual International IEEE EMBS Conference. [3122-3125].
[11]. Epifano I and Ayala G (2002) A random set view of texture classification. IEEE Trans. Image Processing. 11(8),
[859-867].
[12]. Fadi Abu Amara and Abdel Qadar (2007) Detection of breast cancer using independent component analysis. IEEE
EIT Proceedings.[236- 241].
[13]. Gering D, Eric W, Grimson L and Kikinis R (2002) Recognizing deviations from normalcy for brain tumor
segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI), Tokyo Japan.pp:[388-
39]).
[14]. Gupta R and Undril P (1995) The use of textureanalysis to delineate suspicious masses in mammograohy. Physics in
Medicine & Biology.40,[835-855].
[15]. Haney SM, Thompson PM, Cloughesy TF, Alger JR and Toga AW (2001) Tracking tumor growth rates in patients
with malignant gliomas: a test of two algorithms. AJNR Am. J. Neuroradiology. 22,[73-82].
[16]. Hinz M, Pohle R, Shin H and Tonnies KD (2002) Region-based interactive 3D image analysis of structures in
medical data by hybrid rendering. Proc. SPIE in Visualization, Image-Guided Procedures, and Display. 4681, [388-
395].
[17]. Jason J. Corso, Eitan Sharon and ShishirDube (2008) Efficient Multilevel Brain Tumor Segmentation with Integrated
Bayesian Model Classification. IEEE Transaction on Medical Imaging. 27, [148-155].
[18]. Jolesz FA (1997) Image-guided procedures and the operating room of the future. Radiology.204,[,601-612].
[19]. Krishnan K and Atkins MS (1998) Segmentation of multiple sclerosis lesions in MRI – an image analysis approach.
Proc of the SPIE Medical Imaging. 338, [1106-1116].
[20]. Lihua Li, WeidongXu, Zuobao Wu, Angela Salem and Claudia Berman (2007) A new computerized method for
missed cancer detection in screening mammography. Proc. IEEE Natnl. Conf. on Integration Technol. pp: [21-25].

39