Awesome

SFADA-UWF-SLO

Advancing UWF-SLO Vessel Segmentation with Source-Free Active Domain Adaptation and a Novel Multi-Center Dataset (MICCAI 2024 Early accept 🎉)

Introduction 📑

This project introduces a new setting in medical image segmentation, termed Source-Free Active Domain Adaptation (SFADA). SFADA aims to facilitate cross-center medical image segmentation while protecting data privacy and reducing the workload on medical professionals. By requiring only minimal labeling effort, SFADA achieves effective model transfer and results comparable to those of fully supervised approaches.

Fig. 1. Visual comparison of traditional training and our Source-Free Active Domain Adaptation (SFADA) training. <img width="833" alt="1727953214369" src="https://github.com/user-attachments/assets/897352e9-78e1-4ba5-ab2d-8ca610a33599">

How to Run the Code 🛠

Thanks for your interest, code and data are being organized and will be online soon (hope before miccai)!

Dataset 📊

For PRIME-FP20, please refer to this IEEE article and dataset link.

For Center A,

For Center B,

Thanks for your interest, busy recently, code and data are being organized and will be online later.

Citation 📖

If you find our work useful or relevant to your research, please consider citing:

@article{wang2024advancing,
  title={Advancing UWF-SLO Vessel Segmentation with Source-Free Active Domain Adaptation and a Novel Multi-Center Dataset},
  author={Wang, Hongqiu and Luo, Xiangde and Chen, Wu and Tang, Qingqing and Xin, Mei and Wang, Qiong and Zhu, Lei},
  journal={arXiv preprint arXiv:2406.13645},
  year={2024}
}

Comparison with Other Methods 📈

We acknowledge the developers of the comparative methods in ADA4MIA here.