The paper titled “Comparative Study of Machine Learning Models for Brain Tumor Classification Using MRI Images” investigates the application of machine learning techniques for the automated classification of brain tumors using Magnetic Resonance Imaging (MRI) data. The primary objective of this research is to evaluate and compare the performance of several machine learning algorithms in accurately identifying different types of brain tumors from MRI scans. In this study, the Brain Tumor MRI dataset obtained from Kaggle is utilized. The dataset contains MRI images categorized into four classes: glioma tumor, meningioma tumor, pituitary tumor, and no tumor. These categories represent different clinical conditions observed in brain MRI scans. Before model training, several preprocessing techniques are applied, including grayscale conversion, image resizing, and pixel normalization, to standardize the dataset and improve the quality of the input data. In this study, the Brain Tumor MRI dataset obtained from Kaggle is utilized. The dataset contains MRI images categorized into four classes: glioma tumor, meningioma tumor, pituitary tumor, and no tumor. These categories represent different clinical conditions observed in brain MRI scans. Before model training, several preprocessing techniques are applied, including grayscale conversion, image resizing, and pixel normalization, to standardize the dataset and improve the quality of the input data. Following preprocessing, the MRI images are transformed into numerical feature representations that machine learning algorithms can process. The study evaluates three classification models: Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR). These algorithms are trained using the processed MRI dataset and subsequently tested to assess their classification performance. To evaluate model effectiveness, several performance metrics are employed, including accuracy, precision, recall, and F1-score. Experimental results demonstrate that the Random Forest model achieves the highest overall performance, outperforming the other algorithms in terms of classification accuracy and stability. The results indicate that ensemble-based learning methods are particularly effective at capturing complex patterns in MRI brain tumor images. Overall, this research highlights the potential of machine learning approaches to support automated medical image analysis for brain tumor detection and classification. Such systems may assist healthcare professionals in improving diagnostic efficiency, enabling earlier detection and supporting more informed clinical decision-making.
Rayhan Muhammad Abrar (Sun,) studied this question.