Coarse Retinal Lesion Annotations Refinement via Prototypical Learning

TL;DR

This paper introduces a prototype learning-based network that refines coarse retinal lesion annotations into detailed pixel-level masks, improving segmentation accuracy and generalization across datasets.

Contribution

It presents a novel annotation refinement method using prototype learning and a weighing module, enhancing generalization and handling small lesions effectively.

Findings

Significant improvement over baseline in mask refinement accuracy

Effective cross-dataset and cross-class generalization

Prototype weighing module enhances performance on challenging cases

Abstract

Deep-learning-based approaches for retinal lesion segmentation often require an abundant amount of precise pixel-wise annotated data. However, coarse annotations such as circles or ellipses for outlining the lesion area can be six times more efficient than pixel-level annotation. Therefore, this paper proposes an annotation refinement network to convert a coarse annotation into a pixel-level segmentation mask. Our main novelty is the application of the prototype learning paradigm to enhance the generalization ability across different datasets or types of lesions. We also introduce a prototype weighing module to handle challenging cases where the lesion is overly small. The proposed method was trained on the publicly available IDRiD dataset and then generalized to the public DDR and our real-world private datasets. Experiments show that our approach substantially improved the initial coarse mask and outperformed the non-prototypical baseline by a large margin. Moreover, we demonstrate the usefulness of the prototype weighing module in both cross-dataset and cross-class settings.