R2AoP: Reliable and Robust Angle of Progression Estimation from Intrapartum Ultrasound

2026-05-20

AI Summary

This work addresses the susceptibility of angle of progression (AoP) estimation in intrapartum transperineal ultrasound to imaging noise, boundary ambiguity, and geometric amplification of local segmentation errors. To mitigate these issues, the authors propose the R2AoP framework, which enhances segmentation robustness through a three-branch local structure-aware backbone network and introduces a confidence-weighted contour fitting mechanism to suppress the propagation of geometric errors. Furthermore, a lightweight test-time adaptation strategy—requiring no target-domain annotations—is devised to improve model generalization. Evaluated on a multicenter dataset, R2AoP significantly reduces AoP measurement error and boundary deviation, outperforming current state-of-the-art methods.

Abstract

Accurate estimation of the Angle of Progression (AoP) from intrapartum transperineal ultrasound is critical for objective assessment of labor progression, yet remains highly sensitive to imaging noise, boundary ambiguities, and the geometric amplification of local segmentation errors. We propose R2AoP, a reliable and robust AoP estimation framework that integrates structurally informed segmentation and confidence-guided geometric modeling to achieve stable and reproducible measurements. A three-branch local-structure-enhanced backbone improves the delineation of the pubic symphysis (PS) and fetal head (FH), while confidence-weighted contour fitting explicitly suppresses the influence of unreliable boundary points in AoP computation. To further improve performance under heterogeneous acquisition conditions, we introduce a lightweight geometry-reliable test-time adaptation strategy as an auxiliary component, enabling stable inference without target annotations. Extensive evaluations on multi-center benchmarks demonstrate consistent reductions in AoP error and boundary metrics compared with state-of-the-art AoP methods. Our source code is available at https://github.com/baiyou1234/R2AoP.

Problem

• Angle of Progression
• intrapartum ultrasound
• segmentation error
• boundary ambiguity
• imaging noise

Innovation

• Angle of Progression
• robust segmentation
• confidence-weighted fitting
• test-time adaptation
• intrapartum ultrasound