<![CDATA[Brain tumor is a dangerous disease that requires accurate diagnosis, but medical datasets often suffer from class imbalance, resulting in bias in deep learning-based classification models. This study proposes using Categorical Focal Cross Entropy (CFCE) in a Convolutional Neural Network (CNN) to address this issue by comparing it with Categorical Cross-Entropy (CCE). CFCE is designed to emphasize minority class samples and hard-to-classify examples, thereby reducing the dominance of the majority class. Experiments were conducted on a brain tumor dataset with class imbalance, where the CNN model with CFCE achieved 84.57% accuracy, 83.57% precision, 85.27% recall, and 83.97% F1-score, outperforming the model with CCE (81.30% accuracy, 81.77% precision, 82.83% recall, and 81.15% F1-score). These results show that Focal Loss effectively improves the classification performance on imbalanced data, with a better ability to detect brain tumors, especially in the minority class. This study contributes to developing a more robust and reliable deep learning-based diagnosis system for medical applications.]]>
Copyrights © 2026
