1. INTRODUCTION:

All of us know that cell is the fundamental unit for all living things. If cells are damaged, our body produces newer cells to replace the damaged or old ones^1-2. The unnecessary, unregulated growth of cells leads to the formation of tumor⁴. A brain tumor is defined the abnormal growth of superfluous cells in central nervous system or brain⁵. According to the nature of the tumor, it can be classified as primary (main) or secondary (metastatic)^7-8. Primary brain tumors originated and tend to reside in the brain itself¹⁶.

Primary tumors are categorized into either benign or malignant. Table 1 clearly distinguishes both categories. It is very difficult to define the degree of malignancy or aggressiveness of a brain tumor i.e., to sort a brain tumor as “benign” or “malignant” as several issues other than pathological aspects. Metastatic (secondary) brain tumors cancer cells that initiate growing in any part of the body and stretch to the brain. For instance, breast or lung cancer cells are often spread to the brain via the bloodstream. All metastatic brain tumors are malignant (brain cancer).

Table 1: Comparison between Benign and Malignant Tumor

Benign Tumor	Malignant Tumor (Brain Cancer)
Distinct borders	Invasive borders.
Rarely spreads	Often spreads within the brain and spine. However, rarely spread to other parts of the body.
Less harm, if not located at vital area	Life- threatening and invasive
Slow Growth	Rapid Growth
Surgery is the effective solution	Surgery is the effective solution

World Health Organization (WHO) classified tumors into four grades (grade1, grade 2, grade 3 and grade 4) based on the (degree) severity of the malignancy²². The assignment of the grade is based on the appearance of the tumor cells using some characteristic measures of the tumor cells such as rate of the growth, appearance (similarity to normal cells), dead tumor cells in the center of the tumor (especially grade four), blood supply and invasive potential. First grade tumors are the smallest amount of malignant and tumors grow very slowly. These tumors have a common appearance and only surgery is the effectual treatment for this grade of tumor. The second grade tumors have slow growth and have a slightly abnormal. There is no clear demarcation between second and third grade tumors. Third grade tumor cells are aggressively replicating the uncharacteristic cells which develop into nearby normal brain tissue. Fourth grade tumors are considered as most dangerous malignant tumors. These tumor cells appearances is very different from normal cells and reproduce rapidly¹⁷. These cells simply develop into neighboring normal brain tissue. These tumors form new blood vessels so they can maintain their rapid growth. They also have areas of dead cells in their center²⁰. A metastatic brain tumor is formed by primary cancer cells from any part of the body (for example, lung, colon, kidney and breast) which stretch to the brain. The risk factors for brain tumors can broadly be classified into either environmental or genetic¹⁹. The environmental factors includes

· Being exposed to poisonous substances i.e., air pollution, chemicals etc

· Smoking and consuming alcohol

· Working in chemical or petroleum industries

· Experiencing viruses and common infections

· Having a history of head trauma, epilepsy, seizures or convulsions

· Using common medications like birth control pills, sleeping pills, headache remedies, over-the-counter pain treatments and antihistamines.

· Very slight increased risk of a brain tumor associated with using a cell phone for 10 years or more.

Genetic factors refer to conditions or diseases inherited within families. Only 5–10% of all cancer is actually inherited from one generation to another in a family (also called hereditary).

There are lot of methods and techniques to detect and segment the brain tumor from the input test image. Based on the techniques applied, they divided into,

· Edge based techniques

· Region based techniques

· Threshold based techniques

· Clustering based techniques

As far as edge based method is concerned, the harsh variations in the intensity values is the major concern for the segmentation of the tumor. In threshold based techniques, the success of the brain tumor extraction is based on the selection of the proper threshold value³. In region based techniques, the brain tumor image is clustered into number of regions having dissimilar uniqueness. When it comes to clustering based brain tumor detection and segmentation, brain tumor image is divided into number of segments or clusters based on the image characteristics such as texture, color or intensity^{6, 9}. The classification based on the allocation of same group of pixels into the same cluster. The segmentation is the most complicated stage in computer vision and image processing^18,21. In the proposed approach, segmentation process divided an image into a set of different clusters based on intensity attribute^10-15.

2. METHODOLOGY:

The proposed approach for the segmentation and detection of brain tumor is explained as follows.

Step 1: Test image is obtained from image database which is collection of brain tumor images.

Step 2: Pre-processing of the test image. If the image is in RGB color space, the image should be transformed to its gray scale version. The image also resized to 250 * 250 to the efficient analysis of the tumor images.

Step 3: The image enhancement operation is performed on the pre processed image to remove the noisy pixels.

Step 4: The intensity image is converted into binary image using global threshold method, Otsu (threshold value is 0.5 as default).

Step 5: Removes all connected components (objects) from a binary image that have less than 100 pixels using the operation called area opening (bware a open command of MATLAB).

Step 6: Discrete wavelet transform executes single-level two-dimensional wavelet decomposition with respect to particular wavelet decomposition filters.

In MATLAB, The command [cA, cH, cV, cD] = dwt2(X,'wname') calculates the approximation coefficients matrix cA and details coefficients matrices cH, cV, and cD (horizontal, vertical, and diagonal, respectively), obtained by wavelet decomposition of the input matrix X.

Step 7: Principal component analysis (PCA) is a statistical approach that utilizes an orthogonal transformation to transforms a set of observations of possibly correlated into a set of values called principal components (linearly uncorrelated variables). Principal component analysis is performed on image after DWT.

In MATLAB, coeff = pca(X) returns the principal component coefficients for the n-by-p data matrix X. Rows of X correspond to observations and columns correspond to variables. Each column of coeff contains coefficients for one principal component, and the columns are in descending order of component variance. By default, pca centers the data and uses the singular value decomposition (SVD) algorithm.

Step 8: Construct GLCM (gray-level co-occurrence matrix) from image. A gray level co-occurrence matrix (GLCM) contains information about the positions of pixels having similar gray level values. In feature extraction, relevant information is extracted from input data using GLCM.

In MATLAB glcm = graycomatrix(I) creates a gray-level co-occurrence matrix (GLCM) from image I. graycomatrix creates the GLCM by calculating how often a pixel with gray-level (grayscale intensity) value i occurs horizontally adjacent to a pixel with the value j. Each element (i,j) in glcm specifies the number of times that the pixel with value i occurred horizontally adjacent to a pixel with value j.

The computation of gray-level co-occurrence matrix (G) from input image matrix (I) is illustrated in fig 1. Element (1,1) in the GLCM contains the value 1 because there is only one instance in the image where two, horizontally adjacent pixels have the values 1 and 1. Element (1,2) in the GLCM contains the value 2 because there are two instances in the image where two, horizontally adjacent pixels have the values 1 and 2. graycomatrix continues this processing to fill in all the values in the GLCM.

Fig. 1 Computation of gray-level co-occurrence matrix form image matrix (Image Courtesy: Mathworks)

Step 9: Properties of gray-level co-occurrence matrix

In MATLAB, stats = graycoprops (glcm, properties) calculates the statistics specified in properties from the gray-level co-occurence matrix glcm. glcm is an m-by-n-by-p array of valid gray-level co-occurrence matrices. If glcm is an array of GLCMs, stats is an array of statistics for each glcm. graycoprops normalizes the gray-level co-occurrence matrix (GLCM) so that the sum of its elements is equal to 1. Each element (r,c) in the normalized GLCM is the joint probability occurrence of pixel pairs with a defined spatial relationship having gray level values r and c in the image²³. graycoprops uses the normalized GLCM to calculate the following properties.

(a) Contrast is a statistical property which can be computed as the intensity contrast between a pixel and its neighbor over the whole image. The contrast range can be defined as [0 (size (GLCM, 1)-1)^2]. The value 0 indicates constant image (No contrast). The contrast can be computed as

(b) Correlation is the property which explains the correlation between pixel and its neighbor over the whole image. Correlation may be either positive as ‘+1’ (perfectly positively correlated image) or negative as ‘-1’ (perfectly negatively correlated image. The correlation can be computed as,

(c) Energy is the sum of squared elements in the GLCM. The range is [0 1]. For Constant image, energy is ‘1’. Energy can be computed as,

(d) Homogeneity computes the closeness (range of 0 to 1) of the distribution of elements in the GLCM to the GLCM diagonal. It can be defined as,

Step 10: Train SVM classifier with training data.

In MATLAB, The svmtrain function uses an optimization method to identify support vectors s_i, weights α_i, and bias b that are used to classify vectors x according to the following equation:

where k is a kernel function. In the case of a linear kernel, k is the dot product. If c ≥ 0, then x is classified as a member of the first group, otherwise it is classified as a member of the second group.

Step 11: Classify using support vector machine (SVM)

In MATLAB, Group = svmclassify(SVMStruct,Sample) classifies each row of the data in Sample, a matrix of data, using the information in a support vector machine classifier structure SVMStruct, created using the svmtrain function. Like the training data used to create SVMStruct, Sample is a matrix where each row corresponds to an observation or replicate, and each column corresponds to a feature or variable²³. In this way the malignant and benign tumors are classified.

3. RESULT AND DISCUSSION:

Figure 2 illustrates the process outcome of the proposed approach of segmentation of brain tumor from the test image. Test image is obtained from image database which is collection of brain tumor images. If the image is in RGB color space, the image should be transformed to its gray scale version. The image also resized to 250 * 250 to the efficient analysis of the tumor images. The image enhancement operation is performed on the pre processed image to remove the noisy pixels. The intensity image is converted into binary image using global otsu threshold method (threshold value is o.5). All the connected components (objects) from a binary image that have less than 100 pixels is removed using the operation called area opening.

(a) Test Image

(b) Outcome of threshold process

(c) Tumor Segmentation

(d) Brain tumor detection

Fig. 2 Illustration of the outcome of the proposed approach

Table 2: The extracted features from the outcome of the proposed approach

Sl. No	Image Quality Measure	Image 1	Image 2
1	Mean	0.0028	0.0057
2	Root Mean Square	0.0898	0.0898
3	Standard Deviation	0.0897	0.0896
4	Variance	0.0080	0.0080
5	Contrast	0.2155	0.2791
6	Homogeneity	0.9273	0.9324
7	Skewness	0.3229	1.1708
8	Kurtosis	2.3238	3.2890
9	Energy	0.7378	0.7560
10	Entropy	2.6283	1.6819
11	Correlation	0.0950	0.1791
12	Smoothness	0.9132	0.9448

The extracted features from the outcome of the proposed approach using gray level co-occurrence matrix and other image quality measures is listed on table 2. It’s graphical representation is depicted on fig 3.

Fig. 3 Illustration of extracted features from the proposed approach

4. CONCLUSION:

The proposed approach explained the simple but efficient method for the segmentation and detection of brain tumor from the test image. The segmentation process is performed by otsu global threshold and image area opening is applied to remove the small components form the tumor portion. The gray level co-occurrence matrix and other image quality measures are utilized to compute (extract) the features from the segmented image. Support vector machine classifier is finally classified the tumor, either benign or malignant, based on the extracted features. The experimental analysis demonstrated the competence of the proposed method for detection segmentation of the brain tumor from the test image.

5. ETHICS AND CONSENT:

This article does not contain any studies with human participants or animals performed by any of the authors. No direct participation of human entertains in this article.

6. CONFLICT OF INTEREST:

We are declaring that, there is no conflict of interest regarding the publication of this paper.

7. REFERENCES:

1. S. Pereira, A. Pinto, V. Alves and C. A. Silva, "Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images," in IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1240-1251, May 2016.

2. S. Bauer, "A survey of MRI-based medical image analysis for brain tumor studies", Phys. Med. Biol., vol. 58, no. 13, pp. 97-129, 2013.

3. Kalist V, Ganesan P, Sathish BS, and Jenitha JMM. Possiblistic-Fuzzy C-Means Clustering Approach for the Segmentation of Satellite Images in HSL Color Space. Procedia Computer Science. 57; 2015; 49-56.

4. J.J. Corso, E. Sharon, S. Dube, S. El-Saden, U. Sinha, A. Yuille, "Efficient multilevel brain tumor segmentation with integrated bayesian model classification", IEEE Transactions on Medical Imaging, vol. 27, no. 5, pp. 629-640, 2008.

5. R. A. Heckemann, J. V. Hajnal, P. Aljabar, D. Rueckert, A. Hammers, "Automatic anatomical brain MRI segmentation combining label propagation and decision fusion", Neuro Image, vol. 33, pp. 115-126, 2006.

6. Shaik KB, Ganesan P, Kalist V, and Sathish BS. Comparative Study of Skin Color Detection and Segmentation in HSV and YCbCr Color Space. Procedia Computer Science. 57; 2015; 41-48.

7. M. Huang, W. Yang, Y. Wu, J. Jiang, W. Chen and Q. Feng, "Brain Tumor Segmentation Based on Local Independent Projection-Based Classification," in IEEE Transactions on Biomedical Engineering, vol. 61, no. 10, pp. 2633-2645, Oct. 2014.

8. S. Bauer, L. P. Nolte, M. Reyes, "Fully automatic segmentation of brain tumor images using support vector machine classification in combination with hierarchical conditional random field regularization", Proc. Med. Image Comput. Comput. Assist. Interv., pp. 354-361, 2011.

9. Ganesan P and Shaik KB. HSV color space based segmentation of region of interest in satellite images. 2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT). 2014; 101-105.doi: 10.1109/ICCICCT.2014.6992938

10. Sajiv G and Ganesan P. Comparative Study of Possiblistic Fuzzy C-Means Clustering based Image Segmentation in RGB and CIELuv Color Space. International Journal of Pharmacy & Technology. 8(1); 2016; 10899-10909.

11. Malay Bhushan, Niraj Bishwash, and kalist V. Wireless Power Transfer Platform for Smart Home Appliances. International Journal of Pharmacy & Technology. 8(3); 2016; .15669-15674.

12. Sajiv G. Unsupervised Clustering of Satellite Images in CIELab Color Space using Spatial Information Incorporated FCM Clustering Method. International Journal of Applied Engineering Research. 10(20); 2015.

13. Sathish BS, Ganesan P and Khamar Basha.Shaik. Color Image Segmentation based on Genetic Algorithm and Histogram Threshold. International Journal of Applied Engineering Research. 10(6); 2015; 123-127.

14. Thakur M, Raj I and Ganesan P. The cooperative approach of genetic algorithm and neural network for the identification of vehicle License Plate number. International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS). 2015; 1-6.

15. Ganesan P and B. S. Sathish. Automatic Detection of Optic Disc and Blood Vessel in Retinal Images using Morphological Operations and Ipachi Model. Research J. Pharm. and Tech. 10(8): August 2017; 2602-2607.

16. Wulandari, R. Sigit and M. M. Bachtiar, "Brain Tumor Segmentation to Calculate Percentage Tumor Using MRI," 2018 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC), Bali, Indonesia, 2018, pp. 292-296.

17. Huang Meiyan, Wei Yang, Wu Yao, Jiang Jun, Chen Wufan, Qianjin Feng, "Brain Tumor Segmentation Based on Local Independent Projection-based Classification", IEEE Transactions on Biomedical Engineering, 2013.

18. Ganesan P, M.Ganesh , L.M.I.Leo Joseph and V.Kalist, “ Central Retinal Vein Occlusion: An Approach for the Detection and Extraction of Retinal Blood Vessels”, J. Pharm. Sci. & Res. Vol. 10(1), 2018, 192-195.

19. D. Bhattacharyya, T. H. Kim, "Brain tumor detection using MRI image analysis", Commun. Comput. Inform. Sci., vol. 151, pp. 307-314, 2011.

20. C. L. Biji, D. Selvathi, A. Panicker, "Tumor detection in brain magnetic resonance images using modified thresholding techniques", Commun. Comput. Inform. Sic., vol. 4, pp. 300-308, 2011.

21. Ganesan P,, “Detection and Segmentation of Retinal Blood Vessel in Digital RGB and CIELUV color space Fundus Images”, Research J. Pharm. and Tech. 11(6): 2018, 2326-2330.

22. T. M. Hsieh, Y. M. Liu, C. C. Liao, F. Xiao, I. J. Chiang, J. M. Wong, "Automatic segmentation of meningioma from non-contrasted brain MRI integrating fuzzy clustering and region growing", BMC Med. Informat. Decision Making, vol. 11, pp. 54, 2011.

23. https://www.mathworks.com/help/matlab/

Received on 08.02.2019 Modified on 10.03.2019

Research J. Pharm. and Tech. 2019; 12(7):3564-3568.

DOI: 10.5958/0974-360X.2019.00608.5