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


  • Song Jiang Department of Biochemistry, Huzhou Institute Of Biological Products Co., Ltd., China
  • Yuan Gu Department of Statistics, The George Washington University, Washington, DC, USA
  • Ela Kumar Department of Computer Science and Engineering,Koneru Lakshmaiah Education Foundation Deemed to be University,Vaddeswaram, India



MRI, brain tumor, image, classification, model


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




How to Cite

Song Jiang, Yuan Gu, Ela Kumar. Magnetic Resonance Imaging (MRI) Brain Tumor Image Classification Based on Five Machine Learning Algorithms. Cloud Computing and Data Science [Internet]. 2023 May 11 [cited 2023 Jun. 5];4(2):122-33. Available from: