English

W-net: Simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network

Image and Video Processing 2020-06-12 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Segmentation of multiple anatomical structures is of great importance in medical image analysis. In this study, we proposed a W\mathcal{W}-net to simultaneously segment both the optic disc (OD) and the exudates in retinal images based on the multi-task learning (MTL) scheme. We introduced a class-balanced loss and a multi-task weighted loss to alleviate the imbalanced problem and to improve the robustness and generalization property of the W\mathcal{W}-net. We demonstrated the effectiveness of our approach by applying five-fold cross-validation experiments on two public datasets e\_ophtha\_EX and DiaRetDb1. We achieved F1-score of 94.76\% and 95.73\% for OD segmentation, and 92.80\% and 94.14\% for exudates segmentation. To further prove the generalization property of the proposed method, we applied the trained model on the DRIONS-DB dataset for OD segmentation and on the MESSIDOR dataset for exudate segmentation. Our results demonstrated that by choosing the optimal weights of each task, the MTL based W\mathcal{W}-net outperformed separate models trained individually on each task. Code and pre-trained models will be available at: \url{https://github.com/FundusResearch/MTL_for_OD_and_exudates.git}.

Keywords

Cite

@article{arxiv.2006.06277,
  title  = {W-net: Simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network},
  author = {Hongwei Zhao and Chengtao Peng and Lei Liu and Bin Li},
  journal= {arXiv preprint arXiv:2006.06277},
  year   = {2020}
}
R2 v1 2026-06-23T16:13:48.212Z