ERSR: An Ellipse-constrained pseudo-label refinement and symmetric regularization framework for semi-supervised fetal head segmentation in ultrasound images

TL;DR

This paper introduces ERSR, a semi-supervised framework for fetal head ultrasound segmentation that refines pseudo-labels with ellipse fitting and enforces symmetry-based consistency, achieving state-of-the-art results.

Contribution

The paper presents a novel semi-supervised approach combining ellipse-constrained pseudo-label refinement and symmetry regularization for improved fetal head segmentation.

Findings

Achieves Dice scores over 92% with only 10% labeled data.

Outperforms existing methods on HC18 and PSFH benchmarks.

Effectively handles ultrasound image noise and shape variability.

Abstract

Automated segmentation of the fetal head in ultrasound images is critical for prenatal monitoring. However, achieving robust segmentation remains challenging due to the poor quality of ultrasound images and the lack of annotated data. Semi-supervised methods alleviate the lack of annotated data but struggle with the unique characteristics of fetal head ultrasound images, making it challenging to generate reliable pseudo-labels and enforce effective consistency regularization constraints. To address this issue, we propose a novel semi-supervised framework, ERSR, for fetal head ultrasound segmentation. Our framework consists of the dual-scoring adaptive filtering strategy, the ellipse-constrained pseudo-label refinement, and the symmetry-based multiple consistency regularization. The dual-scoring adaptive filtering strategy uses boundary consistency and contour regularity criteria to evaluate and filter teacher outputs. The ellipse-constrained pseudo-label refinement refines these filtered outputs by fitting least-squares ellipses, which strengthens pixels near the center of the fitted ellipse and suppresses noise simultaneously. The symmetry-based multiple consistency regularization enforces multi-level consistency across perturbed images, symmetric regions, and between original predictions and pseudo-labels, enabling the model to capture robust and stable shape representations. Our method achieves state-of-the-art performance on two benchmarks. On the HC18 dataset, it reaches Dice scores of 92.05% and 95.36% with 10% and 20% labeled data, respectively. On the PSFH dataset, the scores are 91.68% and 93.70% under the same settings.