Detection and Classification of Brain Tumor Using Machine Learning

Diagnosing a brain tumor typically necessitates the expertise of a radiologist, whose skills and knowledge are essential to the process. Since the overall number of individuals has grown, so too has the quantity of medical data required to be managed, rendering outdated methods extremely costly and inefficient. Many investigators looked into different techniques that had been quick and effective in identifying and categorizing brain tumours. Currently, Machine learning (ML) techniques have gained popularity in the development of computerized systems that can quickly and effectively diagnose or segment brain tumours. The deep learning (DL) enables the application of ML frameworks for brain tumor identification. This paper proposed various ML models to analyze the MRI images. First, preprocessing and augmentation algorithms were applied to the MRI brain images. We evaluated the performance of several models, including LR, SVC, kNN, NB, NN, RF, and K-means clustering. The analysis focused on accuracy, precision, recall, F1-score, and AUC. LR (96%), NN (95%), and RF (96%) showed the highest performance across all metrics, effectively distinguishing between tumor and no-tumor images and providing reliable results.