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

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%.

Classification of Brain Tumor using Dendritic Cell-Squirrel Search Algorithm in a Parallel Environment

“…Due to this, time complexity becomes a measure challenge in medical image analysis. As a result, this paper offers analysis for brain tumor classification method named as Dendritic Cell-Squirrel Search Algorithm-based Classifier [11] in the parallel environment. In this research paper a parallel processing environment is proposed to reduce the execution time.…”

“…After that, segmented image goes for the M feature extraction task, where statistical and texture features are focused. Finally, the feature selection and classification is carried out using particle rider mutual information [11] and dendritic cell-squirrel search based artificial immune classifier [11], respectively. Motivations 1 As mentioned in the introduction, analyzing multidimensional medical imaging is a crucial task.…”

“…5 The previous approaches and existing approaches are time-consuming, have a low convergence rate, are inefficient, and have low accuracy, specificity and sensitivity. The goal of this research is to develop a novel parallel environment for faster brain tumour classification for the newest proposed methods named as dendritic-Squirrel Search Algorithm [11]. To remove noise and artifacts from the image, Region of Interest and Gaussian filters are used.…”

“…The statistical and texture features are taken from each segment to create a feature vector. For feature selection, the Particle Rider Mutual Information [11] is used, which is developed by combining Particle Swarm Optimization [13], Rider Optimization Algorithm [14], and Mutual Information [15]. The selected features are induced by Artificial Immune Classifier (AIC) [16] in order to determine the tumorous regions.…”

“…The selected features are induced by Artificial Immune Classifier (AIC) [16] in order to determine the tumorous regions. The Dendritic Cell-SSA algorithm [11], which combines the dendritic cell algorithm [17] with the Squirrel search algorithm [18], is used to train the Artificial Immune Classifier. The Artificial Immune Classifier weights are optimized using the suggested Dendritic Cell-SSA technique [11].…”