Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/xianlin7/SAMUS
https://github.com/xianlin7/SAMUS
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/xianlin7/SAMUS
- Owner: xianlin7
- License: mit
- Created: 2023-09-09T02:21:49.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-10-09T03:18:40.000Z (over 1 year ago)
- Last Synced: 2024-08-31T17:49:45.995Z (5 months ago)
- Language: Python
- Size: 332 KB
- Stars: 139
- Watchers: 1
- Forks: 12
- Open Issues: 16
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- Awesome-Segment-Anything - [code
README
# SAMUS
This repo is the official implementation for:\
[SAMUS: Adapting Segment Anything Model for Clinically-Friendly and Generalizable Ultrasound Image Segmentation.](https://arxiv.org/pdf/2309.06824.pdf)\
(The details of our SAMUS can be found in the models directory in this repo or in the paper.)
## Highlights
🏆 Low GPU requirements. (one 3090ti with 24G GPU memory is enough)\
🏆 Large ultrasound dataset. (about 30K images and 69K masks covering 6 categories)\
🏆 Excellent performance, especially in generalization ability.
## Installation
Following [Segment Anything](https://github.com/facebookresearch/segment-anything), `python=3.8.16`, `pytorch=1.8.0`, and `torchvision=0.9.0` are used in SAMUS.
1. Clone the repository.
```
git clone https://github.com/xianlin7/SAMUS.git
cd SAMUS
```
2. Create a virtual environment for SAMUS and activate the environment.
```
conda create -n SAMUS python=3.8
conda activate SAMUS
```
3. Install Pytorch and TorchVision.
(you can follow the instructions [here](https://pytorch.org/get-started/locally/))
5. Install other dependencies.
```
pip install -r requirements.txt
```
## Checkpoints
We use checkpoint of SAM in [`vit_b`](https://github.com/facebookresearch/segment-anything) version.
## Data
- US30K consists of seven publicly-available datasets, including [TN3K]( https://github.com/haifangong/TRFE-Net-for-thyroid-nodule-segmentation), [DDTI]( https://github.com/haifangong/TRFE-Net-for-thyroid-nodule-segmentation), [TG3K](https://github.com/haifangong/TRFE-Net-for-thyroid-nodule-segmentation), [BUSI](https://scholar.cu.edu.eg/?q=afahmy/pages/dataset), [UDIAT](http://www2.docm.mmu.ac.uk/STAFF/M.Yap/dataset.php), [CAMUS](http://camus.creatis.insa-lyon.fr/challenge/), and [HMC-QU](https://aistudio.baidu.com/aistudio/datasetdetail/102406).
- All images were saved in PNG format. No special pre-processed methods are used in data preparation.
- We have provided some examples to help you organize your data. Please refer to the file fold [example_of_required_dataset_format](https://github.com/xianlin7/SAMUS/tree/main/example_of_required_dataset_format).\
Specifically, each line in train/val.txt should be formatted as follows:
```
//
```
- The relevant information of your data should be set in [./utils/config.py](https://github.com/xianlin7/SAMUS/blob/main/utils/config.py)
## Training
Once you have the data ready, you can start training the model.
```
cd "/home/... .../SAMUS/"
python train.py --modelname SAMUS --task
```
## Testing
Do not forget to set the load_path in [./utils/config.py](https://github.com/xianlin7/SAMUS/blob/main/utils/config.py) before testing.
```
python test.py --modelname SAMUS --task
```
## Citation
If our SAMUS is helpful to you, please consider citing:
```
@misc{lin2023samus,
title={SAMUS: Adapting Segment Anything Model for Clinically-Friendly and Generalizable Ultrasound Image Segmentation},
author={Xian Lin and Yangyang Xiang and Li Zhang and Xin Yang and Zengqiang Yan and Li Yu},
year={2023},
eprint={2309.06824},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```