Semi-supervised Medical Image Segmentation via Query Distribution Consistency

Official Pytorch implementation of DKUX-Net, from the following paper:

Semi-supervised Medical Image Segmentation via Query Distribution Consistency.
Rong Wu, Dehua Li, and Cong Zhang
DecisionLinnc Dev Group
[Paper] [Poster, ISBI 2024]

---

We propose DKUX-Net, a transformer-based network for Medical Image Segmentation with less model parameters.

Installation

Please look into the INSTALL.md for creating conda environment and package installation procedures.

Training Tutorial

• LA 2018

(Feel free to post suggestions in issues of recommending latest proposed transformer network for comparison. Currently, the network folder is to put the current SOTA transformer. We can further add the recommended network in it for training.)

Results

LA 2018 Trained Models

Coming Soon!

Training

Training and fine-tuning instructions are in TRAINING.md. Pretrained model weights will be uploaded for public usage later on.

Acknowledgement

This repository is built using the timm library.

License

This project is released under the MIT license. Please see the LICENSE file for more information.

Citation

If you find this repository helpful, please consider citing:

@inproceedings{wu2024semi,
  title={Semi-Supervised Medical Image Segmentation Via Query Distribution Consistency},
  author={Wu, Rong and Li, Dehua and Zhang, Cong},
  booktitle={2024 IEEE International Symposium on Biomedical Imaging (ISBI)},
  pages={1--5},
  year={2024},
  organization={IEEE}
}