Optimizing Brain Tumor Segmentation in MRI using Gradient Boosting Models

This study compares two machine learning methods, XGBoost and LightGBM, for brain tumor segmentation in MRI (Magnetic Resonance Imaging) images. Using data from the BRaTS dataset, both models were trained on preprocessed, intensity-based features and evaluated using standard performance metrics. Results show that both algorithms perform well, with LightGBM slightly outperforming XGBoost in terms of accuracy and F1-score. These findings support the use of gradient boosting techniques in automated medical image analysis.