MULTI-CLASS CEREBRAL TUMOR CLASSIFICATION USING DEEP LEARNING

Brain tumor detection and classification play a crucial role in early diagnosis and effective treatment planning.Traditional diagnosis relies heavily on radiologists manually interpreting MRI scans, which can be timeconsuming and prone to human error.This project proposes an automated system for multi-class brain tumor classification using deep learning techniques.The model is trained on T1-weighted contrast-enhanced MRI images, distinguishing between glioma, meningioma, pituitary tumor, and healthy brain scans.Healthy brain data from the IXI dataset is incorporated to ensure balanced classification across categories.A ResNet50-based Convolutional Neural Network (CNN) with transfer learning is employed to improve feature extraction and classification accuracy.The system applies preprocessing, data augmentation, and fine-tuning to enhance performance.By leveraging open-source tools and publicly available datasets, the project ensures accessibility and cost-effectiveness.The proposed solution aims to support neuro-oncology professionals by providing faster and more reliable preliminary diagnoses, reducing the chances of misinterpretation, and assisting in clinical decision-making.This approach demonstrates the potential of deep learning to transform medical imaging into a more efficient and accurate diagnostic tool.