https://github.com/arush18/brain-tumor-detection
Brain Tumor Detection using a VGG16-based CNN to classify MRI scans.
https://github.com/arush18/brain-tumor-detection
anomaly-detection healthcare neural-network opencv unsupervised-machine-learning
Last synced: 3 months ago
JSON representation
Brain Tumor Detection using a VGG16-based CNN to classify MRI scans.
- Host: GitHub
- URL: https://github.com/arush18/brain-tumor-detection
- Owner: arush18
- License: other
- Created: 2025-03-01T11:02:37.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-01T12:02:21.000Z (over 1 year ago)
- Last Synced: 2026-01-03T08:51:33.094Z (6 months ago)
- Topics: anomaly-detection, healthcare, neural-network, opencv, unsupervised-machine-learning
- Language: Jupyter Notebook
- Homepage:
- Size: 121 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# Brain Tumor Detection using Unsupervised Learning
## Overview
This project focuses on detecting brain tumors using unsupervised learning techniques. The goal is to analyze MRI images and segment potential tumor regions without labeled data, leveraging clustering algorithms for anomaly detection.
## Features
- Unsupervised learning approach for brain tumor detection
- Image preprocessing using OpenCV and NumPy
- Feature extraction for clustering
- Implementation of clustering algorithms (e.g., K-Means, DBSCAN)
- Visualization of segmentation results using Matplotlib
## Technologies Used
- Python
- NumPy
- OpenCV (for image processing)
- Scikit-Learn (for clustering algorithms)
- Matplotlib, Seaborn (for visualization)
- Jupyter Notebook (for experimentation and analysis)
## Installation
1. Clone the repository:
```sh
git clone https://github.com/arush18/Brain-Tumor-Detection.git
cd Brain Tumor Detection
```
2. Create a virtual environment (optional but recommended):
```sh
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
```
3. Install dependencies:
```sh
pip install -r requirements.txt
```
## Dataset
The dataset is not included in this repository. You can use publicly available MRI datasets from Kaggle or your own data. Ensure the dataset is structured as follows:
```
/dataset
├── Image1.jpg
├── Image2.jpg
├── ...
```
Modify the script to specify the correct dataset path.
## Usage
Run the Jupyter Notebook to execute the detection pipeline:
```sh
jupyter notebook main.ipynb
```
## Results
- The project outputs segmented tumor regions from MRI scans.
- Visualizations of clustered tumor regions are generated.
- Evaluation metrics include cluster separability and silhouette scores.
## License
This project is licensed under the MIT License.
## Author
Arush