EAUWSeg: Eliminating annotation uncertainty in weakly-supervised medical image segmentation

TL;DR

EAUWSeg introduces a novel weak annotation and learning framework that effectively reduces annotation uncertainty in medical image segmentation, achieving superior performance with less labeling effort.

Contribution

The paper proposes Bounded Polygon Annotation and a tailored learning framework to eliminate annotation uncertainty in weakly-supervised medical image segmentation.

Findings

Outperforms existing weakly-supervised methods

Achieves near fully-supervised performance with less annotation effort

Provides reliable supervision for uncertain regions

Abstract

Weakly-supervised medical image segmentation is gaining traction as it requires only rough annotations rather than accurate pixel-to-pixel labels, thereby reducing the workload for specialists. Although some progress has been made, there is still a considerable performance gap between the label-efficient methods and fully-supervised one, which can be attributed to the uncertainty nature of these weak labels. To address this issue, we propose a novel weak annotation method coupled with its learning framework EAUWSeg to eliminate the annotation uncertainty. Specifically, we first propose the Bounded Polygon Annotation (BPAnno) by simply labeling two polygons for a lesion. Then, the tailored learning mechanism that explicitly treat bounded polygons as two separated annotations is proposed to learn invariant feature by providing adversarial supervision signal for model training. Subsequently, a confidence-auxiliary consistency learner incorporates with a classification-guided confidence generator is designed to provide reliable supervision signal for pixels in uncertain region by leveraging the feature presentation consistency across pixels within the same category as well as class-specific information encapsulated in bounded polygons annotation. Experimental results demonstrate that EAUWSeg outperforms existing weakly-supervised segmentation methods. Furthermore, compared to fully-supervised counterparts, the proposed method not only delivers superior performance but also costs much less annotation workload. This underscores the superiority and effectiveness of our approach.