Co-Seg

KO | EN

gitlite — search

#javascript #hacktoberfest #llm #android #rust #linux #java #awesome #cli #kubernetes #vue #mcp #openai #open-source

(★ 9)

[MICCAI'2025] Co-Seg: Mutual Prompt-Guided Collaborative Learning for Tissue and Nuclei Segmentation

Co-Seg Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# [MICCAI 2025] Co-Seg: Mutual Prompt-Guided Collaborative Learning for Tissue and Nuclei Segmentation

### [ArXiv Paper](https://arxiv.org/abs/2509.06740)

[Qing Xu](https://scholar.google.com/citations?user=IzA-Ij8AAAAJ&hl=en&authuser=1)1,2 [Wenting Duan](https://scholar.google.com/citations?user=H9C0tX0AAAAJ&hl=en&authuser=1)1 [Zhen Chen](https://franciszchen.github.io/)3✉

1University of Lincoln &emsp; 2Univeristy of Nottingham &emsp; 3Yale University &emsp;

✉ Corresponding Author.

-------------------------------------------
![introduction](https://raw.githubusercontent.com/xq141839/Co-Seg/main/method.png)

## 📰News

- **[2025.08.09]** We have released the code for Co-Seg !
## 🛠Setup

```bash
git clone https://github.com/xq141839/Co-Seg.git
cd Co-Seg
```

**Key requirements**: Cuda 12.2+, PyTorch 2.4+

## 📚Data Preparation
- **PUMA**: [Challenge Link](https://puma.grand-challenge.org/)

The data structure is as follows.
```
Co-Seg
├── datasets
│   ├── image_1024
│     ├── training_set_metastatic_roi_001.png
|     ├── ...
|   ├── mask_sem_1024
│     ├── training_set_metastatic_roi_001_nuclei.npy
|     ├── ...
|   ├── mask_ins_1024
│     ├── training_set_metastatic_roi_001_tissue.npy
|     ├── ...
|   ├── data_split.json
```
The json structure is as follows.

{ 
     "train": ['training_set_metastatic_roi_061.png'],
     "valid": ['training_set_metastatic_roi_002.png'],
     "test":  ['training_set_metastatic_roi_009.png'] 
     }

## 🎪Quickstart
* Train the Co-Seg with the default settings:
```python
python train.py --dataset data/$YOUR DATASET NAME$ --sam_pretrain pretrain/sam2_hiera_large.pth
```

## 📜Citation
If you find this work helpful for your project, please consider citing the following paper:
```
@article{xu2025co,
  title={Co-Seg: Mutual Prompt-Guided Collaborative Learning for Tissue and Nuclei Segmentation},
  author={Xu, Qing and Duan, Wenting and Chen, Zhen},
  journal={arXiv preprint arXiv:2509.06740},
  year={2025}
}
```

## Acknowledgements

* [SAM2](https://github.com/facebookresearch/sam2)
* [Medical-SAM-Adapter](https://github.com/SuperMedIntel/Medical-SAM-Adapter)

Co-Seg

Co-Seg Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Co-Seg

Co-Seg Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README