MG-3D

KO | EN

gitlite — search

#javascript #hacktoberfest #react #ai #go #deep-learning #linux #docker #macos #windows #vue #pytorch #ios #openai

(★ 10)

[MIA 2026] MG-3D: Multi-Grained Knowledge-Enhanced Vision-Language Pre-training for 3D Medical Image Analysis

MG-3D 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# MG-3D
This is the implementation of [MG-3D: Multi-Grained Knowledge-Enhanced Vision-Language Pre-training for 3D Medical Image Analysis]([https://arxiv.org/abs/2412.05876](https://www.sciencedirect.com/science/article/pii/S1361841526000964)).

## Table of Contents

- [Requirements](#requirements)
- [Pre-training](#pre-training)
- [Downstream Evaluation](#downstream-evaluation)

## Requirements

Run the following command to install the required packages:

```bash
pip install -r requirements.txt
```

## Preparation
You can download the CT-RATE and CTRG-Chest datasets used in this work via the Hugging Face repository (https://huggingface.co/datasets/ibrahimhamamci/CT-RATE) and Github (https://github.com/tangyuhao2016/CTRG).

## Pre-training

### 1. Pre-processing

Run the following command to pre-process the data:

```angular2
python prepro/prepro_pretraining_data.py
```

to get the following arrow files:

### 2. Pre-training

Now we can start to pre-train the ptunifer model:

```angular2
Single GPU:
bash run_scripts/pretrain.sh

Multiple GPUs:
bash run_scripts/pretrain_multi_gpus.sh
```

### 3. Pre-trained Models

We provide various models for downstream tasks. You can find the [3D Swin-B-47K](https://drive.google.com/file/d/1Aew0la4wPbxOKaF3BCApS15Pv-TYsRQr/view?usp=drive_link), [3D Swin-L-47K](https://drive.google.com/file/d/1--ELM9N13MvJhB82xpiB3pqf29Gg8ICj/view?usp=drive_link), [3D UNet-1.4K](https://drive.google.com/file/d/1uPFzy66FshFebZu9UcT1qse7m0_VI-FS/view?usp=drive_link), and [3D nn-UNet-1.4K](https://drive.google.com/file/d/1IhC9G6T50LhleC31K7fG649UJSVzrENV/view?usp=drive_link).

## Acknowledgement

The code is based on [PTunifier](https://github.com/zhjohnchan/PTUnifier), [MONAI](https://github.com/Project-MONAI/MONAI), [CT-CLIP](https://github.com/ibrahimethemhamamci/CT-CLIP), [M2KT](https://github.com/LX-doctorAI1/M2KT).

We thank the authors for their open-sourced code and encourage users to cite their works when applicable.

## Citation

If you find this repo useful for your research, please consider citing the paper as follows:
```latex
@article{NI2026104027,
title = {MG-3D: Multi-Grained Knowledge-Enhanced Vision-Language Pre-training for 3D Medical Image Analysis},
journal = {Medical Image Analysis},
pages = {104027},
year = {2026},
issn = {1361-8415},
doi = {https://doi.org/10.1016/j.media.2026.104027},
url = {https://www.sciencedirect.com/science/article/pii/S1361841526000964},
author = {Xuefeng Ni and Linshan Wu and Jiaxin Zhuang and Qiong Wang and Mingxiang Wu and Varut Vardhanabhuti and Lihai Zhang and Hanyu Gao and Hao Chen},}
}
```

MG-3D

MG-3D 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

MG-3D

MG-3D 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README