用半监督方法提升胎儿心脏超声图像的分割与分类准确率。
Synergistic Foundation Models for Semi-Supervised Fetal Cardiac Ultrasound Analysis: SAM-Med2D Boundary Refinement and DINOv3 Semantic Enhancement
- 结合SAM-Med2D边界精修与DINOv3语义增强，优化伪标签质量。
- 在FETUS 2026数据集上达到79.99%的Dice系数和41.20%的F1分数。
- 适合关注产前先天性心脏病筛查的医学影像研究者。
我们提出一种用于胎儿心脏超声图像联合分割与分类的半监督框架。基于EchoCare多任务主干网络，方法融合SAM-Med2D进行边界精修，并利用DINOv3提升伪标签质量。引入视图特异性硬掩码与两阶段优化策略：第一阶段采用指数移动平均（EMA）巩固分割能力，第二阶段冻结分割参数并重置分类头以恢复分类性能，同时不损失分割效果。在FETUS 2026排行榜上评估，该方法取得79.99%的Dice相似性系数、61.62%的归一化表面距离和41.20%的F1分数，验证了其在产前先天性心脏病筛查中的有效性。源代码已公开于：https://github.com/2826056177/zcst_fetus2026。
原文摘要 · Abstract (English)
We present a semi-supervised framework for joint segmentation and classification of fetal cardiac ultrasound images. Built upon the EchoCare multi-task backbone, our method integrates SAM-Med2D for boundary refinement and leverages DINOv3 to enhance pseudo-label quality. We introduce view-specific hard masking along with a two-stage optimization strategy: an EMA phase to consolidate segmentation capabilities, followed by a Classification Fine-Tuning phase that freezes segmentation parameters and resets the classification head to recover classification performance without compromising segmentation gains. Evaluated on the FETUS 2026 leaderboard, our method achieves a Dice Similarity Coefficient at 79.99%, Normalized Surface Distance at 61.62%, and F1-score at 41.20%, validating the effectiveness of our approach for prenatal congenital heart disease screening. Source code is publicly available at: https://github.com/2826056177/zcst_fetus2026.
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。