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

TL;DR

R2AoP is a new framework for more accurate and reliable estimation of the Angle of Progression from ultrasound images, combining advanced segmentation, confidence modeling, and test-time adaptation.

Contribution

It introduces a structurally informed segmentation and confidence-guided geometric modeling approach with test-time adaptation for robust AoP estimation.

Findings

Significantly reduces AoP estimation error compared to existing methods.

Demonstrates consistent performance improvements across multi-center datasets.

Provides stable inference without the need for target annotations.

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.