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

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

[arXiv] [BibTeX]

📰News

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

🛠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

📚Data Preparation

The structure is as follows.

NuSegDG
├── datasets
│   ├── image_1024
│     ├── TCGA-21-5784-01Z-00-DX1.png
|     ├── ...
|   ├── mask_1024
│     ├── TCGA-21-5784-01Z-00-DX1.png
|     ├── ...

🎈Acknowledgements

Greatly appreciate the tremendous effort for the following projects!

• SAM
• Conv-LoRA