Detection of Brain Cancer through Enhanced Particle Swarm Optimization in Artificial Intelligence Approach

Abstract

Brain cancer is deadly and requires prompt detection and treatment. We propose a complete brain cancer detection method using binary encoding, adaptive thresholding, edge-based segmentation, particle swarm optimization (PSO), wavelet transform, and neural networks. First, binary encoding converts categorical patient data and medical history information into binary vectors for fast analysis. Adaptive thresholding then handles image lighting and contrast to optimize brain image segmentation. Brain tumor boundaries are identified via edge-based segmentation. This method isolates tumor areas for investigation by recognizing significant pixel intensities. Particle swarm optimization optimizes segmentation algorithm settings, enhancing efficiency and accuracy. Wavelet transform captures local and global brain picture changes, extracting tumor-related information. This method gives a complete visual representation, improving categorization. Finally, utilizing the collected attributes, a neural network model classifies brain pictures as malignant or non-cancerous. The neural network learns the complicated correlations between retrieved variables and brain cancer to classify accurately and automatically. A dataset of brain pictures, comprising malignant and non-cancerous instances, evaluates the proposed approach. The proposed approach accurately detects brain tumors in experiments. Binary encoding, adaptive thresholding, edge-based segmentation, particle swarm optimization, wavelet transform, and neural networks can help medical professionals diagnose and treat brain cancer early.