用双一致性学习提升低标注胎儿心脏超声分割与诊断精度
Dual Agreement Consistency Learning with Foundation Models for Semi-Supervised Fetal Heart Ultrasound Segmentation and Diagnosis
- 融合预训练超声模型与卷积网络，通过异构协同训练利用无标签数据
- 在多中心数据集上达到59.66的Dice分数和42.82的NSD值
- 适合医疗影像低标注场景，尤其适用于胎儿心脏超声分析
先天性心脏病（CHD）筛查依赖于胎儿超声心动图中多个标准心脏视图的精确分析，但受限于标注数据少和图像质量差异大，构建可靠的人工智能模型仍具挑战。本文提出FM-DACL，一种针对FETUS 2026挑战赛的半监督双一致性学习框架，用于胎儿心脏超声分割与诊断。该方法将预训练的超声基础模型（EchoCare）与卷积网络通过异构协同训练结合，并采用指数移动平均教师机制，以更充分地利用无标签数据。在多中心挑战数据集上的实验表明，使用异构骨干网络的FM-DACL实现了59.66的Dice分数和42.82的NSD值，验证了所提半监督框架的可行性。结果表明，FM-DACL为低标注环境下异构模型的协同应用提供了一种灵活有效的解决方案。代码已开源：https://github.com/13204942/FM-DACL。
原文摘要 · Abstract (English)
Congenital heart disease (CHD) screening from fetal echocardiography requires accurate analysis of multiple standard cardiac views, yet developing reliable artificial intelligence models remains challenging due to limited annotations and variable image quality. In this work, we propose FM-DACL, a semi-supervised Dual Agreement Consistency Learning framework for the FETUS 2026 challenge on fetal heart ultrasound segmentation and diagnosis. The method combines a pretrained ultrasound foundation model (EchoCare) with a convolutional network through heterogeneous co-training and an exponential moving average teacher to better exploit unlabeled data. Experiments on the multi-center challenge dataset show that FM-DACL achieves a Dice score of 59.66 and NSD of 42.82 using heterogeneous backbones, demonstrating the feasibility of the proposed semi-supervised framework. These results suggest that FM-DACL provides a flexible approach for leveraging heterogeneous models in low-annotation fetal cardiac ultrasound analysis. The code is available on https://github.com/13204942/FM-DACL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。