分割
杠杆(统计)
人工智能
计算机科学
图像分割
计算机视觉
模式识别(心理学)
超声波
图像(数学)
超声成像
监督学习
机器学习
训练集
医学影像学
边界(拓扑)
特征提取
作者
Genyu He,Xucheng Xiang,Yijin Gong,Tianzhu Liu,Wei Mei,Shan Tan
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2025-12-15
卷期号:: 3658-3661
标识
DOI:10.1109/bibm66473.2025.11356878
摘要
Fully supervised ultrasound segmentation requires extensive labeled data, which limits its clinical use. While existing semi-supervised methods leverage unlabeled data, they typically treat all regions equally-overlooking critical variations in learning difficulty. We find that boundary and low-contrast regions show persistently low confidence, indicating higher learning difficulty. To address this, we propose a novel framework featuring Bidirectional Replacement and Dynamic Reweighting. Our method constructs easy and hard samples by exchanging regions between images, then applies curriculum-inspired reweighting to adaptively balance their contributions during training. Extensive experiments on three ultrasound datasets demonstrate consistent superiority over state-of-the-art methods under varying supervision levels, confirming effectiveness and robustness.
科研通智能强力驱动
Strongly Powered by AbleSci AI