A novel hybrid approach for the identification of brain regions using magnetic resonance images accountable for brain tumor is presented in this paper. Classification of medical images is substantial in both clinical and research areas. Magnetic resonance
imaging (MRI) modality outperforms towards diagnosing brain abnormalities like brain tumor, multiple sclerosis, hemorrhage, and many more. The primary objective of this work is to propose a threedimensional (3D) novel brain tumor classification model using MRI images with both micro and macroscale textures designed to differentiate the MRI of brain under two classes of lesion, benign and malignant. The design approach was initially preprocessed using 3D Gaussian filter. Based on VOI (volume of interest) of the image, features were extracted using 3D volumetric Square Centroid Lines Gray Level Distribution Method (SCLGM) along with 3D run length and cooccurrence matrix. The optimal features are selected using the proposed refined gravitational search
algorithm (RGSA). Support vector machines, over backpropagation network, and
Cancers that are most common in children aged 0–14 are brain and central nervous system (CNS) tumors (21%) [
Representation of a 3D data in the form of 2D projected slices results in loss of information and may lead to erroneous interpretation of results [
Ushizima et al. in [
Applicability of 3D texture analysis for extracting additional information from MR images (GCM and run length) and obtaining imperceptible quantitative individual information from MR images of the brain in epilepsy type EPM1 patients was carried out in [
Li et al. [
The proposed computeraided diagnosis system categorizes the tumor detected regions as malignant or benign. It aids the radiologists in recognizing tumor diagnosis. The system in the first phase identifies suspicious lesions at a high sensitivity, which involves a feature extraction process using volumetric analysis on the MRI scans. The second phase aims to detect the tumor and to reduce the number of false positives without decreasing the sensitivity drastically.
The problem of brain tumor detection using MR images consists of the major phases in the proposed classification framework. They are (a) micromacro feature extraction for each voxel of VOI as 3D volumetric data, (b) optimal feature subset selection using refined gravitational search algorithm from extracted features, (c) the training process enabling SVM classifier for the optimal feature subset selection, and (d) testing of the final framework using leaveoneout validation. Figure
Framework of the proposed CAD classification model.
320 patient volumes were studied on a 1.5Tesla MRI machine (Avanto, Siemens Medical Solutions, Germany) with T1w 3D magnetization prepared gradient echo (T1w MPR), obtained from hospitals. The pixel resolution was of 256 × 256 (1 × 1 mm), acquired from the 3D volumes having 128 sagittal slices of 1.25 mm.
To facilitate reduction of intensity, homogeneity, and removal of artifacts in MR images, a normalization filter, namely, 3D LoG (Laplacian of Gaussian or Mexican Hat) filter, as represented in (
Normalized 3D LoG filter operation.
Medical images possess a vast amount of texture information relevant to clinical practice. The objective of the feature extraction is to characterize an image to be recognized by measurements, whose values are very similar to those for objects in the same category but very different from those for objects in different categories [
Feature extraction is the numerical computation of a characteristic or an attribute on a digital image which well describes its texture properties [
All possible features are to be extracted towards diagnosing a VOI in the MR image. The extracted feature provides the characteristics of the input type to the classifier by considering the description of the relevant properties of the image into feature vectors. Local features at each point of VOI are to be computed by analyzing the spatial distribution of grey values. Hence a highly defined set of statistical features should be derived to determine the micromacro texture features. In Figure
Expert level draw on each volume of interest (VOI).
The feature extraction model called Square Centroid Lines Gray Level Distribution Method (SCLGM) for detecting calcifications in 2D mammogram [
Along with the 3D gray level cooccurrence matrices (GLCM) [
In this paper it is intended to extend the Square Centroid Lines Gray Level Distribution Method (SCLGM) feature extraction method for volumetric data, by quantifying the spatial distribution of the square; this approach encodes the spatial interdependency of the cells in all directions. The lowest square includes the segmented area with zero background [
Thirteen directions and offset for 3D images.
Sl. number  Offset  Degree, direction ( 

1  0, 1, 0  0°, 0° 
2  −1, 1, 0  45°, 0° 
3  −1, 0, 0  90°, 0° 
4  −1, −1, 0  135°, 0° 
5  0, 1, −1  0°, 45° 
6  0, 0, −1  0°, 90° 
7  0, −1, −1  0°, 135° 
8  −1, 0, −1  90°, 45° 
9  1, 0, −1  90°, 135° 
10  −1, 1, −1  45°, 45° 
11  1, −1, −1  45°, 135° 
12  −1, −1, −1  135°, 45° 
13  1, 1, −1  135°, 135° 
Threedimensional directions drawn towards a VOI.
A set of statistics is computed before extracting micromacro textural features after defining
The textural parameters for the proposed work are calculated in several directions and pixel distances. Mean value for different pixel distances and directions are also computed. Each feature with textural property is used to differentiate the tumor tissues from selected VOI. A set of statistical features are extracted based on 3D Square Centroid Lines Gray Level Distribution Method, 3D GLCM, and 3D run length features. The 61 textural parameters are computed for each centroid as neighbor along 13 directions. All of these texture features are calculated for each VOI.
There arises a need to select most potential features that are highly related to particular classes for classification. This is known as optimal informative feature vector. These features are extracted from an existing feature set to describe the target conceptions of machine learning in classification. The objective is to trace the best minimum subset in the original element set, rather than transforming the data to an entirely new set of dimensions. All extracted features with pooled texture measures are analysed as possibly highly correlated features [
The classical gravity search algorithm is based on the law of gravity (every particle attracts another particle by means of some gravitational force) and mass interaction [
The developed algorithm is based on the interaction of masses steered by the approximation of Newton’s laws of gravity and motion. The refined gravity search algorithm is as follows.
Identify the search space.
Generate initial population of
Fitness evaluation for each agent is calculated in volume of extracted features in 3D axis,
Compute
Calculate the total force in different directions.
Calculate acceleration and velocity.
For each mass
Evaluate
Repeat Steps
Return the best fitness computed at final iteration as a global fitness and the positions of the corresponding agent at specified dimensions as the global solution of that problem.
To improve the performance of RGSA, Bernoulli updating of
Thus, the proposed refined gravity search algorithm provides a wellbalanced mechanism in enhancing exploration and exploitation abilities. The performance simulation results show that RGSA attains promising results and outperforms the classical GSA. The
Parameters of refined GSA (RGSA).
RGSA parameters  Parametric values 

Number of agents  100 
Maximum number of iterations (stop criteria)  500 
Objective function  Minimization 

100 
Classification is a procedure for sorting pixels and assigning them to specific categories. It is about predicting unknown class of an observation. Statistical analysis involves relationship with the variables to a model developed. Models include neural networks,
In classification, if the characteristics or attributes (predictor variable) of a class are known, individual objects might be identified as belonging or not belonging to that class. This transformed attribute used to define the hyperplane is called a feature. Feature selection stage chooses the most optimal attributes. A set of features that labels one instance (i.e., a row of predictor values) is called a vector. SVM technique separates the identified classes with a particular hyperplane to the nearest point in the dataset [
SVM classification.
The basic principle of SVM is to search for optimal hyperplane with maximal distance of the nearest samples from each class. Consider the images to be classified as
The optimal classifying plane and the support vectors are depicted in Figure
Parameters of SVM classifier.
SVM parameters  Parametric values 

Simulation time  50 ms 
Bias value  1 
Weights assigned  Random initialization 
Number of selected features  0.7 
In this paper, along with the proposed RGSA, the SVM classifier is used for brain tumor detection. The realized SVM classifier avoids overtraining and performs better generalization. The classifier is evaluated for performance and the results are compared with a standard BPN and
For implementing the proposed methodologies, the test data considered is of 320 realtime brain volume images. Leaveoneout classification (LOO) method is used to build the classifier with training and testing datasets. LOO approach is a special case of the
The extended volumetric Square Centroid Lines Gray Level Distribution Method for volumetric images enhanced the classification accuracy of the diagnosis system. Based on the thirteen centroid lines, 61 features are extracted; each was represented by thirteen vectors, that is,
The proposed methodology extracted a total of 77 features. In this case, refined gravitational search algorithm (RGSA) is applied for feature selection; the obtained selected features are ranked with respect to the number of occurrences and fitness function criteria. 28 features are observed to be the most prominent ranked optimal subselected features out of which 16 features comprised from the 3D extended gray level squared centroid method are extracted [
Histogram analysis of entropy feature set.
Features extracted from the integrated 3D approach.
MRI: original
Variational intensity (GLCM)
Theta
Gray level centroid extraction
Sharpness (RLM feature)
Tumor segmentation results on realtime datasets: (a) original MRI segmentation by (b) expert, (c) 2D GLCM+2D RLM+2D centroid model, and (d) proposed 3D GLCM+3D RLM+3D centroid model.
On analysis of global classifier, the classification is performed and compared with BPN,
The evaluation of the classifier depends on the misclassification rate. The sensitivity and specificity values are used to compute misclassification rate and success of the diagnostic system of the classifier. Sensitivity is the probability of positive diagnosis test with true cases of tumor defined as
Performance of the classifiers.
Classifier  Training stage efficiency  Validation stage efficiency  

Mean  STD  RMSE  MAE  Mean  STD  RMSE  MAE  
Proposed SVM classifier  100  0  0.004  0.231  98.45  4.4  0.101  0.281 

97.34  0.75  0.125  102.33  90.12  5.6  0.183  138.33 
BPN [ 
98.34  1.01  0.128  155.45  89  5.9  0.175  177.32 
Classification accuracy for the considered classifiers.
The accuracy of the model depends on discrimination between true negatives and false negatives. Accuracy is measured by the area under the ROC curve. The area under a ROC curve (
ROC curve for various classifiers.
The optimal operating points of the three classifiers are computed at (FP = 0.15, TP = 0.94) for the SVM, (FP = 0.20, TP = 0.89) for the
Average results on the 3D feature extraction model for various classifiers on realtime 320 patient data volumes.
Classifier  Specificity %  Sensitivity %  Accuracy %  ROC ( 
Mean square error 

BPN [ 
68.17  89.58  88.85  0.89  0.21 

76.19  91.84  91.14  0.93  0.10 
Developed SVM classifier 





The support vector machine classifier, which classifies the patients to the class which is most probable, will result in one patient data being wrongly classified, leading to a correct classification rate of 98% for the 30 patients sample dataset. This is visualized in Figure
Scatter plot of realtime sample set (30) on SVM classifier for benign and malignant tumor in realtime image dataset. Here “
Scatter plot of realtime sample set (30) on
Scatter plot of realtime sample set (30) on BPN classifier for benign and malignant tumor in realtime image dataset. Here “
The proposed refined gravitational search algorithm creates a set of solutions over single result to overcome the trap of local optimum. The exploration feature enhances the RGSA algorithm as a promising method for feature selection over a high dimension space. Table
Performance analysis of classifiers and feature extraction, both 2D and 3D.
Texture analysis  Classifier  Accuracy % w/o feature selection  Accuracy % with feature selection 

BPN  72.45  81.2  
2D GLCM + 2D RUN LENGTH + 2D SGLDM [ 

84.34  89.45 
SVM  89.55  91.02  


Proposed 3D GLCM + 3D RUN LENGTH + 3D SGLDM  BPN  81.65  88.85 

89.55  91.14  
SVM  90.78  98.4 
Feature selection improvement of proposed RGSA and GSA.
Feature selection improvement of proposed RGSA and traditional GSA.
In this research paper, the proposed RGSA is applied to select features and optimize SVM parameters simultaneously. GSA is a powerful global optimization algorithm but leads to exploration and exploitation tradeoff as other optimization algorithms [
This paper presented a new approach towards identification of the brain regions responsible for brain tumor employing an improved version of gravitational search optimization algorithm for optimal feature selection and high dimensional SVM classifier. The feature extraction stage is an extension of the 3D VOI volumetric model using squared gray level centroid method combining the cooccurrence and run length features which resulted in promising outputs. Thus, it is inferred that the best performance of SVM classifier resulted in better testing performance with a lower error and higher accuracy.
The present work will aid in analyzing pathologies and increasing the physician towards reliable diagnosis. The proposed texture analysis model provides an automated tumor discrimination process through the optimum features which best characterizes MRI brain benign and malignant tumors. The proposed methodology could be extended to classify different grades of cancer (e.g., glioma and meningioma) and degree of malignancy.
See Table
Features  Formula 

Run length features  
Short Run Emphasis (SRE) 

Long Run Emphasis (LRE) 

Low Gray Level Run Emphasis (LGRE) 

High Gray Level Run Emphasis (HGRE) 

Short Run Low Gray Level Run Emphasis (SRLGE) 

Short Run High Gray Level Run Emphasis (SRHGE) 

Long Run Low Gray Level Run Emphasis (LRLGE) 

Long Run High Gray Level Run Emphasis (LRHGE) 

Gray Level Nonuniformity (GLNU) 

RunLevel Nonuniformity (RLNU) 

Run Percentage (RPC) 



GLCM features  
Entropy 

Homogeneity 

Contrast 

Energy 

Correlation coefficient 

The authors declare that there is no conflict of interests regarding the publishing of this paper.