Optimizing brain tumor classification through feature selection and hyperparameter tuning in machine learning models

Abstract

Accurately classifying brain tumors using images is extremely important for prognosis and treatment planning. In this study, we have developed an optimized approach using machine learning techniques to classify brain tumors. Our method involves preprocessing the images, extracting features, selecting the most significant ones, and tuning the model parameters. We utilized filtering, morphological opening, and normalization techniques to enhance image quality and reduce noise. We have extracted 17 features that capture the characteristics of the tumors and identify the seven most distinguishing features through importance analysis. By employing a range of models such as Random Forest, Support Vector Machines, Extreme Gradient Boosting, K Nearest Neighbors, Categorical Boosting, Extra Trees, and Naive Bayes, we achieve an accuracy of 98.0 % after thorough hyperparameter optimization. This research highlights the impact of the feature selection process, along with model tuning, on maximizing classification performance. This approach provides a framework that enables the diagnosis of brain tumors for enhanced clinical decision-making and patient care.

Keywords

• Brain tumor classification
• Brain cancer
• Brain tumor
• Machine learning
• Hyperparameter tuning
• Feature extraction