https://github.com/XueyuLiu/GBMSeg

The official implementation of the paper 'Feature-prompting GBMSeg: One Shot Reference Guided Training-Free Feature Matching for Glomerular Basement Membrane Segmentation and Quantification.'
https://github.com/XueyuLiu/GBMSeg

Last synced: about 2 months ago
JSON representation

The official implementation of the paper 'Feature-prompting GBMSeg: One Shot Reference Guided Training-Free Feature Matching for Glomerular Basement Membrane Segmentation and Quantification.'

• Host: GitHub
• URL: https://github.com/XueyuLiu/GBMSeg
• Owner: XueyuLiu
• Created: 2023-12-19T13:51:07.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-07-04T02:46:49.000Z (7 months ago)
• Last Synced: 2024-07-25T11:52:47.602Z (6 months ago)
• Language: Jupyter Notebook
• Size: 33.3 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Segment-Anything - [code

README

        
# Feature-prompting GBMSeg: One Shot Reference Guided Training-Free Feature Matching for Glomerular Basement Membrane Segmentation and Quantification


**[Xueyu Liu](https://scholar.google.com.hk/citations?user=jeatLqIAAAAJ&hl=zh-CN), Guangze Shi, Rui Wang, Yexin Lai, Jianan Zhang, Lele Sun, Quan Yang, Yongfei Wu*, Weixia Han, Ming Li, and Wen Zheng**


1[Taiyuan University of Technology](https://www.tyut.edu.cn/),  

2[The Second Affiliated Hospital of Shanxi Medical University](https://www.sydey.com/)， 

3[Shanxi Provincial People's Hospital](https://www.sxsrmyy.com/)

### 🚀🚀This work has been accepted by MICCAI2024!🚀🚀

We present GBMSeg, a training-free framework that automates the segmentation and measurement of the glomerular basement membrane (GBM) in TEM using only one-shot reference images. GBMSeg leverages the robust feature matching capabilities of pretrained foundation models (PFMs) to generate initial prompts, designs novel prompting engineering for optimized prompting methods, and utilizes a class-agnostic segmentation model to obtain the final segmentation result. 







## Usage 

### Setup 

- Cuda 12.0

- Python 3.9.18

- PyTorch 2.0.0

### Datasets

    ../                          # parent directory

    ├── ./data                   # data path

    │   ├── reference_image      # the one-shot reference image

    │   ├── reference_mask       # the one-shot reference mask

    │   ├── target_image         # testing images

### Generate prompt

```

cd GBMSeg/feature-matching

python generate_prompt.py

```

### Automatic prompt engineering

```

cd GBMSeg/tools

python automatic_prompt_engineering.py

```

### Segmentation 

```

mkdir GBMSeg/results

cd GBMSeg/segmenting-anything

python segment.py

```

##  Citation

If you find this project useful in your research, please consider citing:

```BibTeX

@article{liu2024feature,

  title={Feature-prompting GBMSeg: One-Shot Reference Guided Training-Free Prompt Engineering for Glomerular Basement Membrane Segmentation},

  author={Liu, Xueyu and Shi, Guangze and Wang, Rui and Lai, Yexin and Zhang, Jianan and Sun, Lele and Yang, Quan and Wu, Yongfei and Li, MIng and Han, Weixia and others},

  journal={arXiv preprint arXiv:2406.16271},

  year={2024}

}

```

## Acknowledgement

Thanks [DINOv2](https://github.com/facebookresearch/dinov2), [SAM](https://github.com/facebookresearch/segment-anything). for serving as building blocks of GBMSeg.