README.md

metadata

title: Brain Tumor Classification
emoji: 🌍
colorFrom: pink
colorTo: blue
sdk: streamlit
sdk_version: 1.41.1
app_file: app.py
pinned: false
license: mit
short_description: Brain tumours Classification model

Brain Tumour Detection API This repository provides a Python-based API for detecting brain tumours from medical images. The solution uses deep learning models to identify tumours and includes an interactive notebook for running the detection pipeline.

Table of Contents Overview Features Setup and Installation Usage Model and Methodology Results Contributing License Overview Brain tumours are serious medical conditions requiring early detection for effective treatment. This project provides an automated approach to detecting brain tumours from medical imaging data using a convolutional neural network (CNN)-based classifier. The API is implemented in Python and uses Jupyter Notebook for demonstration.

Features Deep Learning-based Detection: Utilizes CNNs for identifying tumours in MRI scans. Interactive Notebook: Includes a notebook for experimenting with the detection pipeline. REST API Ready: Easily adaptable for deployment as a REST API. Scalable Model: Suitable for integration into larger medical imaging platforms. Setup and Installation Clone the repository:

git clone https://github.com/bhuvannv13/Brain_Tumour_detection_api.git cd Brain_Tumour_detection_api Install the required Python packages:

pip install -r requirements.txt Ensure you have Jupyter Notebook installed for running the interactive notebook:

pip install notebook (Optional) Set up a virtual environment to isolate dependencies:

python -m venv env source env/bin/activate # On Windows: .\env\Scripts\activate Usage Open the Jupyter Notebook:

jupyter notebook "Brain Tumour Detection.ipynb" Follow the steps in the notebook to load the model, preprocess data, and make predictions.

To adapt the project for API deployment, consider using Flask or FastAPI. Refer to the code structure and ensure the model file is saved for reuse.

Model and Methodology Data Preprocessing: The input MRI scans are preprocessed for model compatibility, including resizing, normalization, and augmentation. Model Architecture: The project employs a CNN architecture optimized for medical image analysis. Evaluation Metrics: The model's performance is evaluated using accuracy, precision, recall, and F1-score. Training: Ensure proper training data with tumour and non-tumour classifications for optimal results. Results Achieves high accuracy in detecting tumours from MRI scans. Visualizes predictions with overlays to assist in understanding model decisions. Contributing Contributions are welcome! To contribute:

Fork the repository. Create a new branch for your feature or bug fix. git checkout -b feature-name Commit your changes and push to the branch. git push origin feature-name Create a pull request describing your changes. License This project is licensed under the MIT License. See the LICENSE file for details.

For questions or feedback, please reach out via the repository's Issues section. Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference