This project uses a U-Net-based deep learning model for segmenting brain tumors from MRI images. The model has been trained on the LGG Segmentation Dataset and performs binary segmentation to identify tumor regions in MRI scans.
- Deep Learning Model: A U-Net architecture for accurate tumor segmentation.
- Preprocessing: Normalizes and resizes MRI images to match the model input.
- Metrics: Includes Dice Coefficients and Intersection Over Union (IoU) for evaluation.
- Web Application: A user-friendly web app (built with Python and Django) allows users to upload MRI scans and get predictions. (Link to be added soon.)
The model achieves high accuracy with Dice Coefficients and IoU metrics.
- Add web app deployment link.
- Improve model generalization for unseen datasets.
Special thanks to the creators of the LGG Segmentation Dataset.
This project is licensed under the MIT License. See LICENSE for details.