Particle Rider Mutual Information and Dendritic-Squirrel Search Algorithm With Artificial Immune Classifier for Brain Tumor Classification

2021 ◽  
Author(s):  
Rahul Ramesh Chakre ◽  
Dipak V Patil
Keyword(s):  
Brain Tumor ◽  
Mutual Information ◽  
Visual Information ◽  
Search Algorithm ◽  
Imaging Modality ◽  
Texture Features ◽  
Magnetic Resonance Images ◽  
Tumor Classification ◽  
Superior Performance ◽  
Artificial Immune

Abstract Magnetic Resonance Images (MRI) is an imperative imaging modality employed in the medical diagnosis tool for detecting brain tumors. However, the major obstacle in MR images classification is the semantic gap between low-level visual information obtained by MRI machines and high-level information alleged by the clinician. Hence, this research article introduces a novel technique, namely Dendritic-Squirrel Search Algorithm-based Artificial immune classifier (Dendritic-SSA-AIC) using MRI for brain tumor classification. Initially the pre-processing is performed followed by segmentation is devised using sparse fuzzy-c-means (Sparse FCM) is employed for segmentation to extract statistical and texture features. Furthermore, the Particle Rider mutual information (PRMI) is employed for feature selection, which is devised by integrating Particle swarm optimization, Rider optimization algorithm and mutual information. AIC is employed to classify the brain tumor, in which the Dendritic-SSA algorithm designed by combining dendritic cell algorithm and Squirrel search algorithm (SSA). The proposed PRMI-Dendritic-SSA-AIC provides superior performance with maximal accuracy of 97.789%, sensitivity of 97.577% and specificity of 98%.

scholarly journals Hybrid RGSA and Support Vector Machine Framework for Three-Dimensional Magnetic Resonance Brain Tumor Classification

2015 ◽  
Vol 2015 ◽  
pp. 1-14 ◽  
Author(s):  
R. Rajesh Sharma ◽  
P. Marikkannu
Keyword(s):  
Brain Tumor ◽  
Magnetic Resonance ◽  
Gravitational Search Algorithm ◽  
Three Dimensional ◽  
Magnetic Resonance Images ◽  
Tumor Classification ◽  
Classification Model ◽  
Support Vector ◽  
Preliminary Evaluation ◽  
Distribution Method

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 three-dimensional (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, andk-nearest neighbor are used to evaluate the goodness of classifier approach. The preliminary evaluation of the system is performed using 320 real-time brain MRI images. The system is trained and tested by using a leave-one-case-out method. The performance of the classifier is tested using the receiver operating characteristic curve of 0.986 (±002). The experimental results demonstrate the systematic and efficient feature extraction and feature selection algorithm to the performance of state-of-the-art feature classification methods.

scholarly journals Brain Tumor Classification of MRI Images Using Deep Convolutional Neural Network

2021 ◽  
Vol 38 (4) ◽  
pp. 1171-1179
Author(s):  
Swaraja Kuraparthi ◽  
Madhavi K. Reddy ◽  
C.N. Sujatha ◽  
Himabindu Valiveti ◽  
Chaitanya Duggineni ◽  
...  
Keyword(s):  
Neural Network ◽  
Brain Tumor ◽  
Magnetic Resonance ◽  
Data Augmentation ◽  
Magnetic Resonance Images ◽  
Tumor Classification ◽  
Support Vector ◽  
Svm Classifier ◽  
Tumor Type

Manual tumor diagnosis from magnetic resonance images (MRIs) is a time-consuming procedure that may lead to human errors and may lead to false detection and classification of the tumor type. Therefore, to automatize the complex medical processes, a deep learning framework is proposed for brain tumor classification to ease the task of doctors for medical diagnosis. Publicly available datasets such as Kaggle and Brats are used for the analysis of brain images. The proposed model is implemented on three pre-trained Deep Convolution Neural Network architectures (DCNN) such as AlexNet, VGG16, and ResNet50. These architectures are the transfer learning methods used to extract the features from the pre-trained DCNN architecture, and the extracted features are classified by using the Support Vector Machine (SVM) classifier. Data augmentation methods are applied on Magnetic Resonance images (MRI) to avoid the network from overfitting. The proposed methodology achieves an overall accuracy of 98.28% and 97.87% without data augmentation and 99.0% and 98.86% with data augmentation for Kaggle and Brat's datasets, respectively. The Area Under Curve (AUC) for Receiver Operator Characteristic (ROC) is 0.9978 and 0.9850 for the same datasets. The result shows that ResNet50 performs best in the classification of brain tumors when compared with the other two networks.

Integrating Morphological Edge Detection and Mutual Information for Nonrigid Registration of Medical Images

2019 ◽  
Vol 15 (3) ◽  
pp. 292-300 ◽  
Author(s):  
Vivek Aggarwal ◽  
Anupama Gupta
Keyword(s):  
Mutual Information ◽  
Edge Detection ◽  
Visual Information ◽  
Medical Images ◽  
Similarity Index ◽  
Structural Similarity ◽  
Magnetic Resonance Images ◽  
Registration Accuracy ◽  
Measure Function ◽  
Improved Performance

Background: Medical images are widely used within healthcare and medical research. There is an increased interest in precisely correlating information in these images through registration techniques for investigative and therapeutic purposes. This work proposes and evaluates an improved measure function for registration of carotid ultrasound and magnetic resonance images (MRI) taken at different times. Methods: To achieve this, a morphological edge detection operator has been designed to extract the vital edge information from images which is integrated with the Mutual Information (MI) to carry out the registration process. The improved performance of proposed registration measure function is demonstrated using four quality metrics: Correlation Coefficient (CC), Structural Similarity Index (SSIM), Visual Information Fidelity (VIF) and Gradient Magnitude Similarity Deviation (GMSD). The qualitative validation has also been done through visual inspection of the registered image pairs by clinical radiologists. Results: The experimental results showed that the proposed method outperformed the existing method (based on integrated MI and standard edge detection) for both ultrasound and MR images in terms of CC by about 4.67%, SSIM by 3.21%, VIF by 18.5%, and decreased GMSD by 37.01%. Whereas, in comparison to the standard MI based method, the proposed method has increased CC by 16.29%, SSIM by 16.13%, VIF by 52.56% and decreased GMSD by 66.06%, approximately. Conclusion: Thus, the proposed method improves the registration accuracy when the original images are corrupted by noise, have low intensity values or missing data.

Brain Tumor Classification Using Enhanced Statistical Texture Features

2020 ◽  
pp. 1-12
Author(s):  
Mallikarjun Mudda ◽  
R. Manjunath ◽  
N. Krishnamurthy
Keyword(s):  
Brain Tumor ◽  
Texture Features ◽  
Tumor Classification

scholarly journals Advanced Technique for Classification and Detection of Brain Tumor in Magnetic Resonance Images

2021 ◽  
Vol 23 (10) ◽  
pp. 136-144
Author(s):  
Sathishkannan R ◽  
◽  
Magesh Kumar B ◽  
Rupashini P R ◽  
Nirmalan R ◽  
...  
Keyword(s):  
Brain Tumor ◽  
Decision Tree ◽  
Texture Features ◽  
Tumor Detection ◽  
Magnetic Resonance Images ◽  
Quality Analysis ◽  
Hormonal Changes ◽  
Mr Image ◽  
Advanced Technique ◽  
Detection Techniques

In the medical world, most challenging disease is Brain tumor. Brain tumors formed inside the brain as an abnormal cell. It is a mass of tissues which results in hormonal changes results in mortality. In the recent years, various brain tumor detection techniques are evolved. We propose, a novel brain tumor detection technique is proposed to detect tumors accurately in given brain MR image and also it classifies the given brain MR image is normal or abnormal. At first the preprocessing is performed by median filtering and segmentation by means of morphological technique. Then the Gray Level Co-occurrence Matrix (GLCM) is applied to extract the texture features. Then, the derived features are applied to classification using three classifiers such as Naïve Bayes, Multilayer perceptron, and Decision Tree C4.5 classifiers. By conducting experiments, the proposed technique is assessed and validated for performance as well as quality analysis based on accuracy, sensitivity and specificity on brain MR images. In experimental section, the performance of all three classifiers are compared in which the decision tree C4.5 algorithm provides better performance with 75% of accuracy, 79% of sensitivity and 56% of specificity.

Combining Wavelet Texture Features and Deep Neural Network for Tumor Detection and Segmentation Over MRI

2019 ◽  
Vol 28 (4) ◽  
pp. 571-588 ◽  
Author(s):  
Srinivasalu Preethi ◽  
Palaniappan Aishwarya
Keyword(s):  
Brain Tumor ◽  
Classification Scheme ◽  
Texture Features ◽  
The Body ◽  
Tumor Classification ◽  
Flower Pollination Algorithm ◽  
Fuzzy C Means Clustering ◽  
Tumor Region ◽  
Occurrence Matrix ◽  
The Brain

Abstract A brain tumor is one of the main reasons for death among other kinds of cancer because the brain is a very sensitive, complex, and central portion of the body. Proper and timely diagnosis can prolong the life of a person to some extent. Consequently, in this paper, we have proposed a brain tumor classification scheme on the basis of combining wavelet texture features and deep neural networks (DNNs). Normally, the system comprises four modules: (i) feature extraction, (ii) feature selection, (iii) tumor classification, and (iv) segmentation. Primarily, we eliminate the noise from the image. Then, the feature matrix is produced by combining wavelet texture features [gray-level co-occurrence matrix (GLCM)+wavelet GLCM]. Following that, we select the relevant features with the help of the oppositional flower pollination algorithm (OFPA) because a high number of features are major obstacles for classification. Then, we categorize the brain image based on the selected features using the DNN. After the classification procedure, the projected scheme extracts the tumor region from the tumor images with the help of the possibilistic fuzzy c-means clustering (PFCM) algorithm. The experimentation results show that the proposed system attains the better result associated with the available methods.

Sign in / Sign up

Export Citation Format

Share Document