Entropy-Guided Agreement-Diversity: A Semi-Supervised Active Learning Framework for Fetal Head Segmentation in Ultrasound

TL;DR

This paper introduces a semi-supervised active learning framework called EGAD that improves fetal head segmentation in ultrasound images by selecting uncertain and diverse samples, leading to higher accuracy with less labeled data.

Contribution

The paper proposes a novel two-stage active learning sampler, EGAD, combining entropy and agreement-diversity scores, along with a consistency-based semi-supervised learning strategy for better fetal ultrasound segmentation.

Findings

Achieved Dice scores of 94.57% and 96.32% on two datasets with minimal labeled data.

Outperformed existing semi-supervised learning models in fetal head segmentation.

Demonstrated robustness across different pregnancy stages.

Abstract

Fetal ultrasound (US) data is often limited due to privacy and regulatory restrictions, posing challenges for training deep learning (DL) models. While semi-supervised learning (SSL) is commonly used for fetal US image analysis, existing SSL methods typically rely on random limited selection, which can lead to suboptimal model performance by overfitting to homogeneous labeled data. To address this, we propose a two-stage Active Learning (AL) sampler, Entropy-Guided Agreement-Diversity (EGAD), for fetal head segmentation. Our method first selects the most uncertain samples using predictive entropy, and then refines the final selection using the agreement-diversity score combining cosine similarity and mutual information. Additionally, our SSL framework employs a consistency learning strategy with feature downsampling to further enhance segmentation performance. In experiments, SSL-EGAD achieves an average Dice score of 94.57\% and 96.32\% on two public datasets for fetal head segmentation, using 5\% and 10\% labeled data for training, respectively. Our method outperforms current SSL models and showcases consistent robustness across diverse pregnancy stage data. The code is available on \href{https://github.com/13204942/Semi-supervised-EGAD}{GitHub}.