PolarMAE: Efficient Fetal Ultrasound Pre-training via Semantic Screening and Polar-Guided Masking

TL;DR

PolarMAE introduces a specialized pre-training framework for fetal ultrasound images, utilizing semantic screening and polar-guided masking to improve efficiency and effectiveness in downstream tasks.

Contribution

It proposes novel US-specific pre-training techniques addressing data redundancy, locality, and polar imaging characteristics, enhancing fetal ultrasound interpretation.

Findings

Achieves state-of-the-art performance on multiple datasets.

Significantly improves pre-training efficiency and scalability.

Effectively captures radial patterns and tissue structures in US images.

Abstract

Intelligent fetal ultrasound (US) interpretation is crucial for prenatal diagnosis, but high annotation costs and operator-induced variance make unsupervised pre-training a highly promising paradigm. However, existing pre-training methods largely ignore US-specific characteristics -- severe data redundancy, fan-shaped locality, and polar coordinate beamforming -- limiting their effectiveness in downstream tasks. To address this, we propose PolarMAE, a novel and efficient pre-training framework tailored for US images. Specifically, to mitigate continuous scanning redundancy, we introduce a Progressive Visual-Semantic Screening (PVSS) that adaptively extracts high-value samples, significantly boosting pre-training efficiency. Furthermore, we design an Acoustic-Bounded Region Constraint (ABRC) to accommodate US locality, forcing the model to focus strictly on valid acoustic regions rather than invalid dark backgrounds. Finally, leveraging the beamforming prior and local details, we propose a Polar-Texture Collaborative Masking (PTCM), enabling the model to capture underlying radial imaging patterns and critical tissue structures. Extensive experiments across diverse datasets and downstream interpretation tasks demonstrate that our method achieves state-of-the-art performance with strong pre-training scalability and efficiency.