Mamba-UNet: Unet-like Pure Visual Mamba for Medical Image Segmentation
Supervised Mamba-UNet -> [Paper Link] Released in 6/Feb/2024.
Semi-Supervised Mamba-UNet -> TBA
3D Mamba-UNet -> TBA
- Pytorch, MONAI
- Some basic python packages: Torchio, Numpy, Scikit-image, SimpleITK, Scipy, Medpy, nibabel, tqdm ......
cd casual-conv1d
python setup.py install
cd mamba
python setup.py install
- Clone the repo:
git clone https://github.com/ziyangwang007/Mamba-UNet.git
cd Mamba-UNet
- Download Pretrained Model
Download through Google Drive for SwinUNet, and Google Drive for Mamba-UNet. in `code/pretrained_ckpt'.
- Download Dataset
Download through Google Drive, and save in `data/ACDC'.
- Train 2D UNet
python train_fully_supervised_2D.py --root_path ../data/ACDC --exp ACDC/unet --model unet
- Train SwinUNet
python train_fully_supervised_2D_ViT.py --root_path ../data/ACDC --exp ACDC/swinunet --model swinunet
- Train Mamba-UNet
python train_fully_supervised_2D_VIM.py --root_path ../data/ACDC --exp ACDC/VIM --model VIM
- Test
python test_2D_fully.py --root_path ../data/ACDC --exp ACDC/xxx --model xxx
SSL4MIS, Segmamba, SwinUNet