Self-Paced Sample Selection for Barely-Supervised Medical Image Segmentation

TL;DR

This paper introduces a self-paced sample selection framework (SPSS) that improves barely-supervised medical image segmentation by reducing pseudo-label noise through uncertainty sampling and contrastive learning, leading to superior results.

Contribution

The paper presents a novel self-paced framework combining uncertainty sampling and contrastive learning to enhance pseudo-label quality in medical image segmentation.

Findings

SPSS outperforms state-of-the-art methods on public datasets.

Self-paced learning improves pseudo-label accuracy.

Contrastive learning enhances feature separability.

Abstract

The existing barely-supervised medical image segmentation (BSS) methods, adopting a registration-segmentation paradigm, aim to learn from data with very few annotations to mitigate the extreme label scarcity problem. However, this paradigm poses a challenge: pseudo-labels generated by image registration come with significant noise. To address this issue, we propose a self-paced sample selection framework (SPSS) for BSS. Specifically, SPSS comprises two main components: 1) self-paced uncertainty sample selection (SU) for explicitly improving the quality of pseudo labels in the image space, and 2) self-paced bidirectional feature contrastive learning (SC) for implicitly improving the quality of pseudo labels through enhancing the separability between class semantics in the feature space. Both SU and SC are trained collaboratively in a self-paced learning manner, ensuring that SPSS can learn from high-quality pseudo labels for BSS. Extensive experiments on two public medical image segmentation datasets demonstrate the effectiveness and superiority of SPSS over the state-of-the-art. Our code is release at https://github.com/SuuuJM/SPSS.