Brain Tumor Detection Using the Cheetah Chase Algorithm: A Novel Approach for Enhanced Accuracy and Efficiency

Precise identification of brain tumors is decisive for effective analysis and treatment preparation. Segmenting tumors from MRI scans presents significant challenges due to their complex anatomical structures and patient variability. The Cheetah Chase Algorithm (CCA) is developed to address these challenges by leveraging the strategic hunting behavior of cheetahs for optimal feature selection and classification. The MRI evaluation process begins with intensity normalization followed by noise reduction before extracting key features using Gray Level Co-occurrence Matrix (GLCM) techniques.CCA facilitates the selection of critical attributes, reducing computational complexity while enhancing interpretability. It's built-in optimization strategy minimizes latency and enhances performance when processing high-dimensional and noisy data. Tumor classification using a Support Vector Machine (SVM) achieves high precision and recall. The experimental findings indicate that CCA achieves swifter operations and higher accuracy than traditional methods. The proposed method achieves superior results to traditional techniques through its 98.7% accuracy. Research findings indicate that the CCA can significantly advance brain tumor detection and medical image processing, contributing to the development of sophisticated diagnostic tools.