Home

Awesome

NuSegDG: Integration of Heterogeneous Space and Gaussian Kernel for Domain-Generalized Nuclei Segmentation

:pushpin: This is an official PyTorch implementation of NuSegDG: Integration of Heterogeneous Space and Gaussian Kernel for Domain-Generalized Nuclei Segmentation

[arXiv] [BibTeX]

<div align="center"> <img width="100%" alt="NuSegDG overview" src="framework.png"/> </div>

πŸ“°News

[2024.08.21] The pre-print paper has been uploaded!

πŸ› Setup

git clone https://github.com/xq141839/NuSegDG.git
cd NuSegDG
conda create -n NuSegDG python=3.10
conda activate NuSegDG
conda install pytorch==1.13.0 torchvision==0.14.0 torchaudio==0.13.0 pytorch-cuda=11.6 -c pytorch -c nvidia
pip install scikit-image -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install albumentations==0.5.2 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pytorch_lightning==1.1.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install monai -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install timm -i https://pypi.tuna.tsinghua.edu.cn/simple

πŸ“šData Preparation

The structure is as follows.

NuSegDG
β”œβ”€β”€ datasets
β”‚   β”œβ”€β”€ image_1024
β”‚     β”œβ”€β”€ TCGA-21-5784-01Z-00-DX1.png
|     β”œβ”€β”€ ...
|   β”œβ”€β”€ mask_1024
β”‚     β”œβ”€β”€ TCGA-21-5784-01Z-00-DX1.png
|     β”œβ”€β”€ ...
|   β”œβ”€β”€ DensityMap
β”‚     β”œβ”€β”€ TCGA-21-5784-01Z-00-DX1.png
|     β”œβ”€β”€ ...

πŸ“œCitation

If you find this work helpful for your project, please consider citing the following paper:

@article{lou2024nusegdg,
  title={NuSegDG: Integration of Heterogeneous Space and Gaussian Kernel for Domain-Generalized Nuclei Segmentation},
  author={Lou, Zhenye and Xu, Qing and Jiang, Zekun and He, Xiangjian and Chen, Zhen and Wang, Yi and Li, Chenxin and He, Maggie M and Duan, Wenting},
  journal={arXiv preprint arXiv:2408.11787},
  year={2024}
}

🎈Acknowledgements

Greatly appreciate the tremendous effort for the following projects!