Machine Learning Techniques for Brain Tumor Classification: A CNN-SVM Approach

Brain tumors are the tenth most common type of tumor affecting people of all ages and are a leading cause of death in humans. However, early detection significantly enhances treatability. Classification of brain tumors typically relies on biopsy, a procedure often deferred until definitive brain surgery. Developing image classification techniques for tumor disorders is crucial to minimize errors in manual diagnoses by radiologists and to accelerate treatment. Advancements in machine learning (ML) offer a promising approach for assisting radiologists in diagnosing tumors using non-invasive magnetic resonance imaging (MRI). This research introduces a network based on feature extraction, where features are derived using a Convolutional Neural Network (CNN) and subsequently classified with a Support Vector Machine (SVM). The process involves transforming the multidimensional feature maps into a 2 D array where each row represents the features of a single image. The proposed method was evaluated using MRI brain images of three types of tumors: pituitary, meningioma, and glioma. The CNN-SVM method attained an accuracy of 98.75%, surpassing the CNN-RF (Random Forest) method, which achieved an accuracy of 96.25%. This result surpasses the performance of many other models. The effectiveness of the proposed approaches is analysed based on different metrics and outcomes compared to various method.