ScribbleVS: Scribble-Supervised Medical Image Segmentation via Dynamic Competitive Pseudo Label Selection

TL;DR

ScribbleVS is a novel framework that leverages scribble annotations for medical image segmentation, using dynamic pseudo-label selection and diffusion to improve accuracy and reduce noise, achieving results comparable to fully supervised methods.

Contribution

The paper introduces ScribbleVS, a new method that effectively learns from scribble annotations by expanding supervision and refining pseudo-labels with dynamic selection modules.

Findings

Achieves segmentation accuracy comparable to fully supervised models.

Effectively reduces noise impact in pseudo-labels.

Demonstrates robustness across multiple medical imaging datasets.

Abstract

In clinical medicine, precise image segmentation can provide substantial support to clinicians. However, obtaining high-quality segmentation typically demands extensive pixel-level annotations, which are labor-intensive and expensive. Scribble annotations offer a more cost-effective alternative by improving labeling efficiency. Nonetheless, using such sparse supervision for training reliable medical image segmentation models remains a significant challenge. Some studies employ pseudo-labeling to enhance supervision, but these methods are susceptible to noise interference. To address these challenges, we introduce ScribbleVS, a framework designed to learn from scribble annotations. We introduce a Regional Pseudo Labels Diffusion Module to expand the scope of supervision and reduce the impact of noise present in pseudo labels. Additionally, we introduce a Dynamic Competitive Selection module for enhanced refinement in selecting pseudo labels. Experiments conducted on the ACDC, MSCMRseg, WORD, and BraTS2020 datasets demonstrate promising results, achieving segmentation precision comparable to fully supervised models. The codes of this study are available at https://github.com/ortonwang/ScribbleVS.