MedSeg: Medical Image Segmentation GUI Toolbox
可视化医学图像分割软件

Get all segmentation baselines without writing any code.
不用写任何代码便可以运行所有分割模型

The current code is designed for Windows, not for Linux.

Install (安装步骤):

conda create -n nnsam python=3.9
conda activate nnsam

Choose a suitable Pytorch with CUDA to install
根据CUDA选择合适版本的Pytorch进行安装

pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

pip install git+https://github.com/ChaoningZhang/MobileSAM.git
pip install timm
pip install git+https://github.com/Kent0n-Li/nnSAM.git

git clone https://github.com/Kent0n-Li/Medical-Image-Segmentation.git
cd Medical-Image-Segmentation
pip install -r requirements.txt

运行可视化软件

python web.py

If you only want to use nnSAM, please install this.
如果你只想运行nnSAM,请访问该代码仓库this

样例数据集：Demo Dataset

Overview 页面总览

Choose Model 选择模型

Import Data 导入你的数据集 （2D: png, 3D: nii.gz)

样例数据集：Demo Dataset

Full Auto 全自动模式，一键完成从数据预处理到训练测试和结果总结

Result Summary 结果总结

Citation

If you find this repository useful for your research, please use the following.

@article{li2023nnsam,
  title={nnSAM: Plug-and-play Segment Anything Model Improves nnUNet Performance},
  author={Li, Yunxiang and Jing, Bowen and Li, Zihan and Wang, Jing and Zhang, You},
  journal={arXiv preprint arXiv:2309.16967},
  year={2023}
}