This project classifies brain tumor MRI scans into four categories using a Convolutional Neural Network (CNN). The categories are:
The goal of this project is to develop a deep learning model that can accurately classify MRI images of brain scans into these four categories. The dataset contains MRI images for each category and is used to train the CNN model. The model performance is evaluated using metrics such as accuracy, confusion matrix, and classification report.
In addition, the trained model is deployed on a web app using the Streamlit library. The app is designed to assist doctors in diagnosing brain tumors by allowing them to upload MRI images and receive real-time classification results.
The dataset used for this project is from the Kaggle competition: Brain Tumor MRI Scans. It contains labeled MRI images of four categories: https://www.kaggle.com/datasets/rm1000/brain-tumor-mri-scans Glioma Tumor Healthy Brain Meningioma Tumor Pituitary Tumor The dataset was downloaded and organized into separate folders for each class.
Convolutional Neural Network (CNN) for image classification. Data Preprocessing using OpenCV for image resizing and normalization. Evaluation Metrics including accuracy, confusion matrix, and classification report. Visualization of predictions, model performance, and class distributions. Model Saving for future use.