极端标签缺乏下的三维超声分割学习
研究提出一种基于教师-学生跨维度知识蒸馏的标签高效三维超声分割方法,用无监督表示学习预训练的二维教师网络指导三维学生网络,在多个三维超声数据集和解剖结构上,即使训练标签少于0.5%,分割精度也持续优于现有最先进技术,并支持更精确评估器官容积特性。
要点
- 二维教师网络经无监督表示学习预训练,将知识蒸馏至三维学生分割网络。
- 在多个三维超声数据集和解剖结构上,训练标签少于0.5%时分割精度仍持续超越现有最先进技术。
- 更优分割支持更精确评估人体器官临床相关容积特性。
核心结论
- 该方法通过解决三维超声数据标签缺乏问题,为深度学习模型更广泛融入医疗保健铺路,可能在研究或临床环境中提供更准确高效的诊断和治疗。
研究设计与样本
- 研究提出基于教师-学生跨维度知识蒸馏框架的标签高效三维超声分割方法;二维教师网络以无监督表示学习预训练,其指导迁移至三维学生分割网络;在多个三维超声数据集和解剖结构上进行实验。
诊断标准与关键数值
- 在多个三维超声数据集和解剖结构上,所提方法在分割精度上持续超越现有最先进技术,即使训练标签少于0.5%。
临床应用与阅片要点
- 更优的分割支持更精确评估人体器官的临床相关容积特性。
- 原文结论认为该方法可能使深度学习模型更广泛融入医疗保健,并在研究和临床环境中可能提供更准确高效的诊断和治疗。
局限性
- 原文未报告局限性。
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
OBJECTIVE: 3-D ultrasound imaging has shown great promise in clinical diagnosis by offering comprehensive volumetric assessment of organs and anatomical structures. Automatic segmentation of these anatomical structures from 3-D ultrasound images plays a critical role in precise evaluation of the clinically relevant volumetric properties of human organs. However, such segmentation algorithms typically demand a large amount of labeled data for training and the labeling process requires considerable expertise and effort, particularly in the 3-D context. In this study, our objective was to achieve accurate and robust 3-D ultrasound segmentation under extreme label deficiency.
METHODS: We proposed a label-efficient 3-D ultrasound segmentation method based on a teacher-student cross-dimensional knowledge distillation framework. A 2-D teacher network, pre-trained with unsupervised representation learning, extracted rich information from ultrasound slices, with its guidance transferred to a 3-D student segmentation network, allowing the 3-D model to learn effective volumetric features from very sparse annotations.
RESULTS: Experiments on multiple 3-D ultrasound datasets and anatomical structures demonstrated that the proposed method consistently surpasses existing state-of-the-art techniques in segmentation accuracy, even when trained with less than 0.5% labeled data. The improved segmentations support more precise evaluation of the clinically relevant volumetric properties of human organs.
CONCLUSION: By addressing the persistent issue of label deficiency in 3-D ultrasound data, our method paves the way for greater integration of deep learning models into health care, potentially offering more accurate and efficient diagnosis and treatment in both research and clinical settings.
引用
- Qin Z, Ban Y, Zhang H, et al. Learning 3-D Ultrasound Segmentation under Extreme Label Deficiency. Ultrasound Med Biol. 2026. PMID: 41771726. doi:10.1016/j.ultrasmedbio.2025.12.014
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。