基于小波频率替换与边缘增强的胎儿超声半监督分割
本研究针对超声图像低对比度与边界模糊问题,提出一种半监督分割框架,利用离散小波变换分解高低频子带,并引入高频替换与边缘增强模块。在PSFHS、HC18、CCAUI三个胎儿超声公开数据集上,仅用10张标注图像平均DSC达0.81和0.91,较FixMatch提升2–3%。
要点
- 高频替换与边缘增强可改善超声模糊边界分割效果
- 仅需10张标注图像即取得较优分割性能,减少标注依赖
- 适用于胎儿超声图像分割的半监督训练策略
核心结论
- 所提框架在有限标注条件下通过频域增强与边缘感知改善超声图像分割精度
研究设计与样本
- 研究类型为方法学实验研究,采用半监督深度学习分割框架
- 使用PSFHS、HC18、CCAUI三个公开胎儿超声分割数据集进行验证
- 以小波变换分解图像高低频子带,并将高频替换策略用于强增强图像
- 引入边缘掩膜增强模块以强化解剖边界
- 仅使用10张标注图像进行模型训练与评估
关键影像表现/征象
- 消融实验证实高频增强与边缘增强组件均有效
诊断标准与关键数值
- 在PSFHS、HC18、CCAUI数据集上平均Dice相似系数分别为0.81和0.91
- 与FixMatch等现有半监督方法相比DSC提升2–3%
临床应用与阅片要点
- 该框架可降低胎儿超声分割对大量标注数据的依赖
- 高频替换与边缘增强策略可提升解剖边界分割稳定性
- 代码开源可复现并迁移至其他超声分割任务
局限性
- 仅使用公开数据集的实验验证,未描述外部临床数据测试
- 摘要未涉及与全监督方法的系统性比较
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: Ultrasound image segmentation remains a significant challenge due to inherent low contrast and blurred anatomical boundaries. Fully supervised deep learning approaches require extensive annotated datasets, which are costly and labor-intensive to acquire. This study aims to develop an effective semi-supervised segmentation framework for ultrasound images with limited annotations.
METHODS: We propose a novel semi-supervised segmentation framework tailored for ultrasound images, leveraging frequency component augmentation and edge mask enhancement to promote structural consistency between weakly and strongly augmented inputs. Specifically, discrete wavelet transform (DWT) is used to decompose ultrasound images into low-frequency and high-frequency sub-bands. A high-frequency component replacement strategy is introduced for strongly augmented images, and an edge mask enhancement module is designed to further emphasize anatomical boundaries.
RESULTS: Experiments conducted on 3 public fetal ultrasound imaging segmentation datasets-PSFHS, HC18, and CCAUI-demonstrate that our method achieves average Dice similarity coefficients (DSC) of 0.81 and 0.91, respectively, using only 10 annotated images. This represents a 2-3% DSC improvement over existing semi-supervised methods such as FixMatch. Ablation studies confirm the effectiveness of both the high-frequency augmentation and edge enhancement components.
CONCLUSION: The proposed framework offers a promising direction for ultrasound image segmentation in settings with limited annotations, effectively improving segmentation accuracy by combining frequency-domain augmentation and edge-aware enhancement. Code will be available at https://github.com/apple1986/WTEM-SemiSeg.
引用
- Yue, Wu, Huang, et al. Wavelet-Based Frequency Replacement and Edge Enhancement for Semi-Supervised Fetal Ultrasound Image Segmentation. J Ultrasound Med. 2026. PMID: 41503872. doi:10.1002/jum.70171
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。