https://github.com/mmasoud1/meshfl

MeshNet distributed learning by using the NVFlare framework
https://github.com/mmasoud1/meshfl

Last synced: about 1 month ago
JSON representation

MeshNet distributed learning by using the NVFlare framework

• Host: GitHub
• URL: https://github.com/mmasoud1/meshfl
• Owner: Mmasoud1
• Created: 2024-09-05T14:58:50.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-11-20T08:32:26.000Z (about 2 months ago)
• Last Synced: 2024-11-20T10:08:39.679Z (about 2 months ago)
• Language: Python
• Size: 266 KB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# MeshFL [![Version](https://img.shields.io/badge/Version-1.0.0-brightgreen)]() [![MIT-License ](https://img.shields.io/badge/license-MIT-green)](https://github.com/Mmasoud1/MeshFL/blob/main/LICENSE) [![PyTorch](https://img.shields.io/badge/PyTorch-Trained%20Model-blue)]()



**[Updates](#Updates)   [Doc](https://github.com/Mmasoud1/MeshFL/wiki/)   [News!](#News)**






 

  


MeshFL is an advanced framework for distributed learning in neuroimaging. Built on the  MeshNet models and  NVFlare, it enables federated training for 3D MRI brain segmentation across decentralized data sites, maintaining privacy and efficiency.

 




 For more information about MeshFL, please refer to this detailed Wiki






## Key Features

* Federated training of the MeshNet model for 3D MRI brain segmentation.

* Supports decentralized learning across multiple sites using NVFlare.

* Automated data handling and splitting.

* Optimized GPU usage.

* Customizable training workflows with integrated Dice score evaluation.






![Interface](https://github.com/Mmasoud1/MeshFL/blob/main/css/images/MeshFL_animated_output.gif)

**MeshFL training and MRI segmentation outputs**



## Getting Started

To start MeshFL, please refer to this steps here

## Updates

* MeshFL  v1.0.0  has been released

## News!

## Contributions and Authorship Guidelines

We welcome contributions to MeshFL! Whether it's bug fixes, new features, or documentation improvements, feel free to submit an issue or a pull request.

If you modify or extend MeshFL in a derivative work intended for publication (such as a research paper or software tool), please cite and acknowledge the original MeshFL project and the original authors. 

We also request that significant contributions to derivative works be recognized by including original authors as co-authors, where appropriate.

## Acknowledgments

[NVFlare:](https://developer.nvidia.com/flare) Federated learning framework. 

[MeshNet:](https://medium.com/pytorch/catalyst-neuro-a-3d-brain-segmentation-pipeline-for-mri-b1bb1109276a) Volumetric dilated convolutional neural network architecture for MRI segmentation.

## Funding

MeshFL release V1.0.0 was funded by the NIH grant xx