Brain Tumor Classification using Convolutional Neural Network with ResNet Architecture

Brain tumors are dangerous, sometimes fatal illnesses that require prompt, accurate diagnosis to enhance patient outcomes. Given the intricacy and diversity of tumor characteristics, manual interpretation of brain MRI data is frequently laborious and prone to human error. This research aims to create an automated system for classifying brain tumors by integrating the Convolutional Neural Network (CNN) algorithm with the ResNet architecture. The suggested approach makes use of 7,023 MRI pictures that have been divided into four categories: non-tumor, pituitary tumor, meningioma, and glioma. Image normalization, grayscale conversion, scaling, and data augmentation methods, including rotation and flipping, were among the preprocessing processes used to enhance model performance. The ResNet design was chosen because it effectively trains deeper networks by utilizing residual connections to prevent vanishing gradient problems. Metrics such as F1-score, accuracy, precision, and recall were used to train and assess the system. According to the testing data, the model performed consistently across all classes and attained an outstanding accuracy of 94.14%. These results validate the promise of deep learning methods, especially CNNs with ResNet enhancements, for classification tasks involving medical images. The system created in this work is a promising tool for assisting clinical decision-making, cutting down on diagnostic time, and improving the accuracy of brain tumor identification and classification.