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

2026-01-24

AI Summary

This work addresses the challenges of scarce annotated data in fetal ultrasound imaging and the performance limitations of existing semi-supervised methods that rely on random sampling. To this end, the authors propose EGAD, a two-stage active learning sampler: it first identifies high-uncertainty samples based on prediction entropy, then refines selection via an Agreement-Diversity score that integrates cosine similarity and mutual information. Additionally, a consistency learning strategy with feature downsampling is introduced. By unifying uncertainty, diversity, and consistency within a single active learning framework, EGAD effectively mitigates overfitting and enhances generalization across gestational weeks. Remarkably, using only 5% and 10% of labeled data, the method achieves average Dice scores of 94.57% and 96.32% on two public datasets, substantially outperforming current semi-supervised approaches.

Technology Category

• Machine Learning: Active Learning
• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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}.

Problem

• fetal ultrasound
• semi-supervised learning
• active learning
• data scarcity
• label efficiency

Innovation

• Active Learning
• Semi-Supervised Learning
• Fetal Head Segmentation
• Entropy-Guided Sampling
• Agreement-Diversity Score