ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling

TL;DR

ProPL introduces a universal semi-supervised framework for ultrasound image segmentation that effectively handles multiple organs and tasks by leveraging prompt-guided decoders and pseudo-label calibration, outperforming existing methods.

Contribution

The paper pioneers a universal semi-supervised approach for ultrasound segmentation, integrating prompt-guided decoders and a new dataset for multiple organs and tasks.

Findings

ProPL outperforms state-of-the-art methods across various metrics.

A new comprehensive ultrasound dataset with 5 organs and 8 tasks is introduced.

ProPL establishes a new benchmark for universal ultrasound segmentation.

Abstract

Existing approaches for the problem of ultrasound image segmentation, whether supervised or semi-supervised, are typically specialized for specific anatomical structures or tasks, limiting their practical utility in clinical settings. In this paper, we pioneer the task of universal semi-supervised ultrasound image segmentation and propose ProPL, a framework that can handle multiple organs and segmentation tasks while leveraging both labeled and unlabeled data. At its core, ProPL employs a shared vision encoder coupled with prompt-guided dual decoders, enabling flexible task adaptation through a prompting-upon-decoding mechanism and reliable self-training via an uncertainty-driven pseudo-label calibration (UPLC) module. To facilitate research in this direction, we introduce a comprehensive ultrasound dataset spanning 5 organs and 8 segmentation tasks. Extensive experiments demonstrate that ProPL outperforms state-of-the-art methods across various metrics, establishing a new benchmark for universal ultrasound image segmentation.