https://github.com/xmed-lab/TP-Mamba

https://github.com/xmed-lab/TP-Mamba

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/xmed-lab/TP-Mamba
• Owner: xmed-lab
• Created: 2024-07-03T13:57:20.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-10-24T15:26:10.000Z (3 months ago)
• Last Synced: 2024-10-25T20:24:37.465Z (3 months ago)
• Language: Python
• Size: 11.7 KB
• Stars: 3
• Watchers: 1
• Forks: 0
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Segment-Anything - [code

README

        




Efficiently Adapting Vision Foundational Models on 3D Medical Image Segmentation 🚀





   



    





    



Official PyTorch implementation for our works on the topic of **efficiently adapting the pre-trained Vision Foundational Models (VFM) on 3D Medical Image Segmentation task**.

[1] ["Tri-Plane Mamba: Efficiently Adapting Segment Anything Model for 3D Medical Images"](https://papers.miccai.org/miccai-2024/paper/2184_paper.pdf) ([MICCAI 2024](https://papers.miccai.org/miccai-2024))

## 🌊🌊🌊 News

💧 ***[2024-10-22]*** Re-organize and Upload partial core codes.

## 🔥🔥🔥 Contributions

We foucs on proposing more advanced adapters or training algorithms to adapt the pre-trained VFM (both ***natural*** and ***medical-specific*** models) on 3d medical image segmentation.

🔥 ***Data-Efficient***: Use less data to achieve more competitive performance, such as semi-supervised, few-shot, zero-shot, and so on.

🔥 ***Parameter-Efficient***: Enhance the representation by lightweight adapters, such as local-feature, global-feature, or other existing adapters. 

## 🧰 Installation

🔨 TODO 

## ⭐⭐⭐ Usage

💡 Supported Adapters

| Name   | Type   | Supported   |

|------------|------------|------------|

| Baseline (Frozen SAM) | None | ✔️|

| LoRA | pixel-independent | ✔️|

| SSF | pixel-independent | TODO |

| multi-scale conv| local | ✔️|

| PPM| local | TODO |

| Mamba| global | TODO |

| Linear Attention| global | TODO |

## 📋 Results and Models

📌 TODO 

## 📚 Citation

If you think our paper helps you, please feel free to cite it in your publications.

📗 TP-Mamba

```bash

@InProceedings{Wan_TriPlane_MICCAI2024,

        author = { Wang, Hualiang and Lin, Yiqun and Ding, Xinpeng and Li, Xiaomeng},

        title = { { Tri-Plane Mamba: Efficiently Adapting Segment Anything Model for 3D Medical Images } },

        booktitle = {proceedings of Medical Image Computing and Computer Assisted Intervention -- MICCAI 2024},

        year = {2024},

        publisher = {Springer Nature Switzerland},

        volume = {LNCS 15009},

        month = {October},

        page = {pending}

}

```

## 🍻 Acknowledge

We sincerely appreciate these precious repositories 🍺[MONAI](https://github.com/Project-MONAI/MONAI) and 🍺[SAM](https://github.com/facebookresearch/segment-anything).