Code for our paper "A Contrastive Consistency Semi-supervised Left Atrium Segmentation Model".

• Proposed a class-aware semi-supervised 3D left atrium segmentaion model.
• Proposed a contrastive consistency loss function in class-level.

The pipeline of our method is shown below:

Python 3.6.2

Pytorch 1.7

CUDA 11.2

Run

train: python train_LA_semi_contrastive.py
test: python test_LA_semi_contrast.py

Please consider citing this project in your publications if it helps your research. The following is a BibTeX reference. The BibTeX entry requires the url LaTeX package.

@article{LIU2022102092,
    title = {A contrastive consistency semi-supervised left atrium segmentation model},
    journal = {Computerized Medical Imaging and Graphics},
    volume = {99},
    pages = {102092},
    year = {2022},
    issn = {0895-6111},
    doi = {https://doi.org/10.1016/j.compmedimag.2022.102092},
    url = {https://www.sciencedirect.com/science/article/pii/S0895611122000659},
｝

The development of this project is based on SegWithDistMap