I prefer to use my other repo MedicalZoo which includes this library along with algorithms for 2D models and multimodal medical image segmentation. Of course this repo is more pure.
Inspired by Pytorch-Medical-Segmentation of Ellis,I wrote this project for 3D medical imaging.I didn't use Torchio as the Dataloader for this project, I just used numpy as the Dataloader,which improved the efficiency of data reading.
This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps.
- pytorch1.7
- python>=3.6
- Clone the repo
git clone https://github.com/JohnMasoner/3D-Medical-Image-Segmentation.git
- Installation the requirements
pip install -r requirement.txt
- Custom the configuration
You can modify the variables in the
hparam.pyto fit your data. - Training
python train.py
- test
- more models
For more details or any questions, please feel easy to contact us by email masoner6429@gmail.com.