DSTCS: Dual-Student Teacher Framework with Segment Anything Model for Semi-Supervised Pubic Symphysis Fetal Head Segmentation

TL;DR

This paper introduces DSTCS, a dual-student teacher framework integrating CNN and Segment Anything Model (SAM) for semi-supervised fetal head and pubic symphysis segmentation, addressing challenges like class imbalance and ambiguous boundaries.

Contribution

The paper presents a novel dual-student teacher architecture combining CNN and SAM, with a cooperative learning mechanism and specialized data augmentation for improved ultrasound segmentation.

Findings

Outperforms existing methods on MICCAI benchmarks

Demonstrates robustness in noisy ultrasound images

Provides reliable clinical segmentation results

Abstract

Segmentation of the pubic symphysis and fetal head (PSFH) is a critical procedure in intrapartum monitoring and is essential for evaluating labor progression and identifying potential delivery complications. However, achieving accurate segmentation remains a significant challenge due to class imbalance, ambiguous boundaries, and noise interference in ultrasound images, compounded by the scarcity of high-quality annotated data. Current research on PSFH segmentation predominantly relies on CNN and Transformer architectures, leaving the potential of more powerful models underexplored. In this work, we propose a Dual-Student and Teacher framework combining CNN and SAM (DSTCS), which integrates the Segment Anything Model (SAM) into a dual student-teacher architecture. A cooperative learning mechanism between the CNN and SAM branches significantly improves segmentation accuracy. The proposed scheme also incorporates a specialized data augmentation strategy optimized for boundary processing and a novel loss function. Extensive experiments on the MICCAI 2023 and 2024 PSFH segmentation benchmarks demonstrate that our method exhibits superior robustness and significantly outperforms existing techniques, providing a reliable segmentation tool for clinical practice.