Incremental learning for exudate and hemorrhage segmentation on fundus images

Wanji He, Xin Wang, Lin Wang, Yelin Huang, Zhiwen Yang, Xuan Yao, Xin Zhao, Lie Ju, Liao Wu, Lin Wu, Huimin Lu, Zongyuan Ge

Research output: Contribution to journalArticleResearchpeer-review

18 Citations (Scopus)

Abstract

Deep-learning-based segmentation methods have shown great success across many medical image applications. However, the custom training paradigms suffer from a well-known constraint of the requirement of pixel-wise annotations, which is labor-intensive, especially when they are required to learn new classes incrementally. Contemporary incremental learning focuses on dealing with catastrophic forgetting in image classification and object detection. However, this work aims to promote the performance of the current model to learn new classes with the help of the previous model in the context of incremental learning of instance segmentation. It enormously benefits the current model when the labeled data is limited because of the high labor intensity of manual labeling. In this paper, on the Diabetic Retinopathy (DR) lesion segmentation problem, a novel incremental segmentation paradigm is proposed to distill the knowledge of the previous model to improve the current model. Remarkably, we propose various approaches working on the class-based alignment of the probability maps of the current and the previous model, accounting for the difference between the background classes of the two models. The experimental evaluation of DR lesion segmentation shows the effectiveness of the proposed approaches.

Original languageEnglish
Pages (from-to)157-164
Number of pages8
JournalInformation Fusion
Volume73
DOIs
Publication statusPublished - Sept 2021

Keywords

  • Incremental learning
  • Knowledge distillation
  • Semantic segmentation

Cite this