东北大学学报(自然科学版) ›› 2026, Vol. 47 ›› Issue (1): 20-30.DOI: 10.12068/j.issn.1005-3026.2026.20250103

• 智慧医疗专栏 • 上一篇    下一篇

均值教师方法在半监督医学图像分割中的应用

杨金柱1,2,3(), 魏美1,2,3, 于琪1,2,3, 孙松1,2,3   

  1. 1.东北大学 计算机科学与工程学院,辽宁 沈阳 110169
    2.东北大学 医学影像智能计算教育部重点实验室,辽宁 沈阳 110169
    3.东北大学 工业智能与系统优化国家级前沿科学中心,辽宁 沈阳 110169
  • 收稿日期:2025-06-07 出版日期:2026-01-15 发布日期:2026-03-17
  • 通讯作者: 杨金柱
  • 作者简介:杨金柱(1979—),男,内蒙古通辽人,东北大学教授,博士生导师.
  • 基金资助:
    国家自然科学基金资助项目(U22A2022)

Application of Mean Teacher Method in Semi-supervised Medical Image Segmentation

Jin-zhu YANG1,2,3(), Mei WEI1,2,3, Qi YU1,2,3, Song SUN1,2,3   

  1. 1.School of Computer Science & Engineering,Northeastern University,Shenyang 110169,China
    2.Key Laboratory of Intelligent Computing in Medical Image,Ministry of Education,Northeastern University,Shenyang 110169,China
    3.National Frontiers Science Center for Industrial Intelligence and Systems Optimization,Northeastern University,Shenyang 110169,China. cn
  • Received:2025-06-07 Online:2026-01-15 Published:2026-03-17
  • Contact: Jin-zhu YANG

摘要:

医学图像分割是临床诊疗的重要技术基础,精准的医学图像分割有助于提升疾病诊断准确率与效率.深度学习方法在该领域取得了显著进展,然而,这类方法高度依赖人工标签数据,而高质量分割标签获取成本高,限制了其实际应用.半监督学习通过联合利用少量标签数据与大量无标签数据,有效缓解了标签匮乏问题.其中,均值教师(mean teacher,MT)是当前主流的半监督学习方法,其通过指数移动平均从无标签数据提取信息,提升模型精度与泛化性能,目前已被广泛应用于医学图像分割.本文对MT进行了深入综述,重点从一致性正则化、不确定性、注意力机制、多任务学习、辅助校正及模型变体等方面介绍其在医学图像分割领域的应用和改进.本文简要分析了MT方法的应用和改进趋势,罗列了医学图像分割中常见对比实验方法、数据集、MT骨干网络和评价指标.最后,讨论了MT在医学图像分割中面对的挑战和未来潜在的研究方向.

关键词: 均值教师, 医学图像分割, 深度学习, 半监督学习, 一致性正则化

Abstract:

Medical image segmentation is an important technical basis for clinical diagnosis and treatment. Accurate medical image segmentation contributes to improving the accuracy and efficiency of disease diagnosis. Deep learning methods have made significant progress in this field. However, these methods are heavily dependent on manually labeled data, and the high cost of obtaining high-quality segmentation labels limits their practical application. Semi-supervised learning effectively alleviates the label scarcity problem by combining a small amount of labeled data with a large amount of unlabeled data. Mean teacher (MT) is a mainstream semi-supervised learning method. It leverages an exponential moving average to extract information from unlabeled data, enhancing model accuracy and generalization performance. Currently, MT has been widely adopted in medical image segmentation. In this paper, MT was comprehensively reviewed, focusing on its application and improvement in the medical image segmentation field from aspects such as consistency regularization, uncertainty, attention mechanism, multi-task learning, auxiliary correction, and model variants. Furthermore, trends in the application and enhancement of MT were briefly analyzed, and commonly used comparative experimental methods, datasets, backbone networks of MT, and evaluation metrics in medical image segmentation were summarized. Finally, existing challenges and potential future research directions in applying MT to medical image segmentation were discussed.

Key words: mean teacher, medical image segmentation, deep learning, semi-supervised learning, consistency regularization

中图分类号: