Optimized Brain Tumor Detection: A Dual-Module Approach for MRI Image Enhancement and Tumor Classification

The proposed method for optimized brain tumor detection utilizes a dual-module approach that enhances MRI image quality and classifies tumor types effectively. Initially, brain MRI images are processed using adaptive Wiener filtering to reduce noise, enhancing the clarity and quality of the images for accurate analysis. Following this, a Radial Basis Function (RBF) neural network is employed for feature extraction, allowing the model to identify relevant characteristics within the MRI scans that are critical for diagnosis. After feature extraction, the process transitions to a post-processing stage, where a Support Vector Machine (SVM) is utilized for classification. This combined ICA-NN-SVM approach facilitates the identification of various abnormalities, specifically meningiomas, gliomas, and pituitary tumors. By integrating advanced noise reduction techniques with robust classification algorithms, this methodology aims to improve the accuracy and reliability of brain tumor detection in clinical settings, ultimately contributing to better patient outcomes and more effective treatment planning. The effectiveness of this dual-module system showcases its potential as a valuable tool in medical imaging and diagnostics.

Index Terms— Magnetic resonance imaging (MRI), image enhancement technique, brain tumor segmentation, neural networks, brain tumor classification.