/bonus

Official implementation of the paper "BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labels"

Primary LanguagePythonMIT LicenseMIT

BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labels

This is the official code for our paper:

BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labels
Yi Lin*, Zeyu Wang*, Dong Zhang, Kwang-Ting Cheng, and Hao Chen

Highlights

  • A boundary mining framework for nuclei segmentation, named BoNuS, which simultaneously learns nuclei interior and boundary information from the point labels.
  • A boundary mining loss that guides the model to learn the boundary information by exploring the pairwise pixel affinity in a multiple-instance learning manner.
  • A nuclei detection module with curriculum learning to detect the missing nuclei with prior morphological knowledge.

Usage

Requirement

conda env create --name bonus --file environment.yml

Data preparation

Training & Evaluation

bash detection.sh
bash segmentation.sh

Citation

Please cite the paper if you use the code.

@article{lin2024bonus,
  title={BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labels},
  author={Lin, Yi and Wang, Zeyu and Zhang, Dong and Cheng, Kwang-Ting and Chen, Hao},
  journal={IEEE Transactions on Medical Imaging},
  year={2024},
  publisher={IEEE}
}