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

Abstract

Magnetic Resonance Imaging is a vital imaging tool for detecting brain malignancies in medical diagnosis. The semantic gap between low-level visual information collected by MRI equipment and high-level information stated by the doctor, on the other hand, is the biggest stumbling block in MR image classification. Large amount of medial image data is generated through various imaging modalities. For processing this large amount of medical data, considerable period of time is required. Due to this, time complexity becomes a measure challenge in medical image analysis. As a result, this paper offers analysis for brain tumour classification method named as Dendritic Cell-Squirrel Search Algorithm-based Classifier in the parallel environment. In this paper a parallel environment is proposed. In the experimentation the input dataset is divided into datasets of equal sizes and given as the input on the multiple cores to reduce the time complexity of the algorithm. Due to this, brain tumor classification becomes faster. Here initially, pre-processing is performed applying Gaussian Filter and ROI, it improves the data quality. Subsequently segmentation is done with sparse fuzzy-c-means (Sparse FCM) for extracting statistical and texture features. Additionally, for feature selection, the Particle Rider mutual information is used, which is created by combining Particle Swarm Optimization (PSO), Rider Optimization Algorithm (ROA), and mutual information. The Dendritic Cell-SSA algorithm, which combines the Dendritic Cell Algorithm and the Squirrel Search Algorithm, is used to classify brain tumors. With a maximum accuracy of 97.79 percent, sensitivity of 97.58 percent, and specificity of 98 percent, the Particle Rider MI-Dendritic Cell-Squirrel Search Algorithm-Artificial Immune Classifier outperforms the competition. The experimental result shows that the proposed parallel technique works efficiently and the time complexity is improved up to 99.94% for Particle Rider MI-Dendritic Cell- Squirrel Search Algorithm-based artificial immune Classifier and 99.92% for Rider Optimization-Dendritic Cell –Squirrel Search Algorithm based Classifier as compared to sequential approach.