https://github.com/SuperMedIntel/Medical-SAM2

Medical SAM 2: Segment Medical Images As Video Via Segment Anything Model 2
https://github.com/SuperMedIntel/Medical-SAM2

deep-learning medical medical-imaging segment-anything segment-anything-2 segment-anything-model segmentation

Last synced: about 2 months ago
JSON representation

Medical SAM 2: Segment Medical Images As Video Via Segment Anything Model 2

• Host: GitHub
• URL: https://github.com/SuperMedIntel/Medical-SAM2
• Owner: SuperMedIntel
• License: apache-2.0
• Created: 2024-07-30T04:49:37.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-09-07T13:53:14.000Z (5 months ago)
• Last Synced: 2024-11-26T01:30:40.525Z (2 months ago)
• Topics: deep-learning, medical, medical-imaging, segment-anything, segment-anything-2, segment-anything-model, segmentation
• Language: Python
• Homepage:
• Size: 2.06 MB
• Stars: 483
• Watchers: 6
• Forks: 60
• Open Issues: 26
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-Segment-Anything - [code

README

        
● Medical SAM 2: Segment Medical Images As Video Via Segment Anything Model 2




    

        

    



Medical SAM 2, or say MedSAM-2, is an advanced segmentation model that utilizes the [SAM 2](https://github.com/facebookresearch/segment-anything-2) framework to address both 2D and 3D medical

image segmentation tasks. This method is elaborated on the paper [Medical SAM 2: Segment Medical Images As Video Via Segment Anything Model 2](https://arxiv.org/abs/2408.00874).

## 🔥 A Quick Overview 

 


 

## 🩻 3D Abdomen Segmentation Visualisation

 


## 🧐 Requirement

 Install the environment:

 ``conda env create -f environment.yml``

 ``conda activate medsam2``

 You can download SAM2 checkpoint from checkpoints folder:

 

 ``bash download_ckpts.sh``

 Further Note: We tested on the following system environment and you may have to handle some issue due to system difference.

```

Operating System: Ubuntu 22.04

Conda Version: 23.7.4

Python Version: 3.12.4

```

We released our pretrain weight [here](https://huggingface.co/jiayuanz3/MedSAM2_pretrain/tree/main)

 ## 🎯 Example Cases

 #### Download REFUGE or BCTV or your own dataset and put in the ``data`` folder, create the folder if it does not exist ⚒️

 

 ### 2D case - REFUGE Optic-cup Segmentation from Fundus Images

**Step1:** Download pre-processed [REFUGE](https://refuge.grand-challenge.org/) dataset manually from [here](https://huggingface.co/datasets/jiayuanz3/REFUGE/tree/main), or using command lines:

 ``wget https://huggingface.co/datasets/jiayuanz3/REFUGE/resolve/main/REFUGE.zip``

 ``unzip REFUGE.zip``

 **Step2:** Run the training and validation by:

 

``python train_2d.py -net sam2 -exp_name REFUGE_MedSAM2 -vis 1 -sam_ckpt ./checkpoints/sam2_hiera_small.pt -sam_config sam2_hiera_s -image_size 1024 -out_size 1024 -b 4 -val_freq 1 -dataset REFUGE -data_path ./data/REFUGE``

 ### 3D case - Abdominal Multiple Organs Segmentation

 

 **Step1:** Download pre-processed [BTCV](https://www.synapse.org/#!Synapse:syn3193805/wiki/217752) dataset manually from [here](https://huggingface.co/datasets/jiayuanz3/btcv/tree/main), or using command lines:

 ``wget https://huggingface.co/datasets/jiayuanz3/btcv/resolve/main/btcv.zip``

 ``unzip btcv.zip``

**Step2:** Run the training and validation by:

 ``python train_3d.py -net sam2 -exp_name BTCV_MedSAM2 -sam_ckpt ./checkpoints/sam2_hiera_small.pt -sam_config sam2_hiera_s -image_size 1024 -val_freq 1 -prompt bbox -prompt_freq 2 -dataset btcv -data_path ./data/btcv``

## 🚨 News

- 24-08-05. Our Medical SAM 2 paper **ranked #1 Paper of the day** collected by AK on Hugging Face 🤗

- 24-08-05. Update 3D example details and pre-processed BTCV dataset download link 🔗

- 24-08-05. Update 2D example details and pre-processed REFUGE dataset download link 🔗

- 24-08-05. Our Medical SAM 2 paper was available online 🥳

- 24-08-05. Our Medical SAM 2 code was available on Github 🥳

- 24-07-30. The SAM 2 model was released 🤩

## 📝 Cite

 ~~~

@misc{zhu_medical_2024,

	title={Medical SAM 2: Segment medical images as video via Segment Anything Model 2},

    author={Jiayuan Zhu and Yunli Qi and Junde Wu},

    year = {2024},

    eprint={2408.00874},

    archivePrefix={arXiv},

    primaryClass={cs.CV}

}

 ~~~