Machine learning for brain tumor classification: evaluating feature extraction and algorithm efficiency

Uncontrolled fast cell growth causes brain tumors, posing a significant threat to global health and leading to millions of deaths annually. Early cancer detection is crucial to save lives. The purpose of this study is to investigates the capability of machine learning algorithms and feature extraction methods to detection and classification of brain tumors. We implemented six machine learning algorithms and three features extraction methods, including Image Loading, HOG, and LBP. The objective of this study is to identify best combination of machine learning and features extraction method for brain tumor detection and classification. This study utilized two Brain Tumor MRI Datasets downloaded from Kaggle. Our analysis revealed that Random Forest emerged as the most effective classifier by achieving an accuracy of 99% with image loading feature extraction method based on different metrics, closely followed by SVM and Logistic Regression. However, performance varied with KNN, Naive Bayes, and Decision Tree, highlighting the importance of tailored approaches for optimal classification accuracy. Further optimization and experimentation are crucial for improving algorithm performance in real-world applications of brain tumor classification. A case study with interpretable machine learning is also presented in the paper.