A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement

TL;DR

This paper introduces a semi-supervised breast ultrasound segmentation framework that uses training-free pseudo-labels generated via vision-language models with simple appearance descriptions, achieving high performance with minimal labeled data.

Contribution

The proposed method leverages appearance-based descriptions for cross-domain pseudo-label generation, enabling scalable semi-supervised segmentation with limited annotations.

Findings

Achieves comparable performance to fully supervised models with only 2.5% labeled data.

Significantly outperforms existing semi-supervised approaches on four BUS datasets.

Demonstrates extensibility to other imaging modalities and diseases.

Abstract

Semi-supervised learning (SSL) has emerged as a promising paradigm for breast ultrasound (BUS) image segmentation, but it often suffers from unstable pseudo labels under extremely limited annotations, leading to inaccurate supervision and degraded performance. Recent vision-language models (VLMs) provide a new opportunity for pseudo-label generation, yet their effectiveness on BUS images remains limited because domain-specific prompts are difficult to transfer. To address this issue, we propose a semi-supervised framework with training-free pseudo-label generation and label refinement. By leveraging simple appearance-based descriptions (e.g., dark oval), our method enables cross-domain structural transfer between natural and medical images, allowing VLMs to generate structurally consistent pseudo labels. These pseudo labels are used to warm up a static teacher that captures global structural priors of breast lesions. Combined with an exponential moving average teacher, we further introduce uncertainty entropy weighted fusion and adaptive uncertainty-guided reverse contrastive learning to improve boundary discrimination. Experiments on four BUS datasets demonstrate that our method achieves performance comparable to fully supervised models even with only 2.5% labeled data, significantly outperforming existing SSL approaches. Moreover, the proposed paradigm is readily extensible: for other imaging modalities or diseases, only a global appearance description is required to obtain reliable pseudo supervision, enabling scalable semi-supervised medical image segmentation under limited annotations.