🆕 Official repo of DiPE.

Diversity-Promoting Ensemble for Medical Image Segmentation

Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Andreea-Iuliana Miron, SAC 2023

📜 Arxiv Link: https://arxiv.org/abs/2210.12388

🌟 Overview

We propose a novel strategy to generate ensembles of different architectures for medical image segmentation, by leveraging the diversity (decorrelation) of the models forming the ensemble. More specifically, we utilize the Dice score among model pairs to estimate the correlation between the outputs of the two models forming each pair. To promote diversity, we select models with low Dice scores among each other.

🔒 License

The present code is released under the Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license.

🖊Citation

Please cite our work if you use any material released in this repository.

@inproceedings{Georgescu-SAC-2023,
  title="{Diversity-Promoting Ensemble for Medical Image Segmentation}",
  author={Georgescu, Mariana-Iuliana and Ionescu, Radu Tudor and Miron, Andreea-Iuliana},
  booktitle={Proceedings of SAC},
  year={2023}, 
}