Developing a UNet3D model for accurate MRI skull stripping using the Calgary Campinas 359 dataset, enhancing neuroimaging preprocessing workflows.
MIT License
This project involves the development of a deep learning model for MRI skull stripping using the Calgary Campinas 359 dataset. The primary goal is to accurately segment brain tissue from MRI scans, which is a crucial preprocessing step for many neuroimaging studies.
T1-weighted volumetric brain MR images used in this project is sourced from the Calgary Campinas 359 Dataset
The model used in this project is a 3D version of the UNet architecture, designed to handle volumetric data such as MRI scans. UNet3D is known for its encoder-decoder structure, which is particularly effective for segmentation tasks in 3D medical imaging.
To run the code in this repository, make sure you have the following dependencies installed:
If you use this code or the UNet model architecture in your work, please cite the original paper of the orignal model:
If you used the dataset in your work, please cite the original paper of it: