Magnetic Resonance Imaging (MRI) Brain Tumor Image Classification Based on Five Machine Learning Algorithms

With the emergence of new technologies, vast amounts data have become pervasive in various aspects social life, including public transportation, community services, and scientific research. As population ages, healthcare has increasingly crucial, reducing burdens, especially hospitals, an urgent issue. For instance, manually managing electronic medical files, such as MRI images, based on their types is practically impossible. However, accurate classification fundamental critical for subsequent tasks, diagnosis. In this article, we utilized machine learning techniques to classify brain tumor images. We employed a range models, k-Nearest Neighbors (k-NN), decision tree, Support Vector Machine (SVM), logistic regression, Stochastic Gradient Descent (SGD). The performance each model type was measured by True Skill Statistics (TSS), results obtained from confusion matrix. showed that k-NN works most efficiently among all those models. due constraints limited running time computational power, further investigation models parameter optimization are necessary future work.