Paper Title
ResNet50-Enhanced CNN for Automated Brain Tumor Detection

Abstract
Accurate and early classification of abnormal brain tumors is critical for effective treatment planning and improving patient outcomes. This study presents a deep learning-based approach for brain tumor classification using the ResNet50 architecture, a residual convolutional neural network known for its robustness in image recognition tasks. Leveraging a publicly available MRI dataset, the model was trained to distinguish between various types of abnormal brain tumors. The performance of ResNet50 was comprehensively evaluated and compared with other conventional convolutional neural networks (CNNs) to assess its effectiveness.Evaluationmetricsincluding accuracy, precision, recall, F1-score, and area under the ROC curve (AUC) were employed to ensure a rigorous performance assessment. The results demonstrate that ResNet50 outperforms standard CNN architectures, achieving high classification accuracy and exhibiting strong generalization capabilities. This study highlights the potential of deep residual networks in assisting medical professionals with reliable and automated brain tumor diagnosis. Keywords - Brain Tumor Classification; ResNet50; Deep Learning; Convolutional Neural Networks (CNNs); Medical Image Analysis; MRI; Tumor Detection; Automated Diagnosis; Residual Networks; Neural Network Evaluation.