This project involves classifying brain tumors using the Xception model, a deep learning Convolutional Neural Network (CNN). The dataset contains 3,060 Brain MRI images categorized into tumorous ("yes") and non-tumorous ("no") classes. The system achieved high performance, with a precision of 0.9899, recall of 0.9767, F1-score of 0.9832, and an AUC of 0.9987. By leveraging transfer learning and deep learning techniques, the model helps in the automated detection and classification of brain tumors, potentially assisting radiologists in diagnosing patients more efficiently.
1. Develop an automated system for detecting and classifying brain tumors using the Xception CNN model.
2. Achieve high accuracy and classification metrics, including precision, recall, F1-score, and AUC.
3. Train the model on a dataset of 3,060 Brain MRI images, divided into tumorous and non-tumorous categories.
4. Utilize Python and TensorFlow to implement the deep learning model.
5. Provide an effective diagnostic tool for healthcare professionals, aiding in the accurate and timely detection of brain tumors.
6. Apply deep learning and transfer learning to enhance the model's ability to generalize and perform well in real-world scenarios.
