[1]黄贤泊,程远志.基于双不确定性引导的抗噪半监督医学图像分割[J].中国医学物理学杂志,2026,43(9):1188-1195.[doi:DOI:10.3969/j.issn.1005-202X.2026.09.005]
　HUANG Xianbo,CHENG Yuanzhi.Noise-resilient semi-supervised medical image segmentation based on dual uncertainty guidance[J].Chinese Journal of Medical Physics,2026,43(9):1188-1195.[doi:DOI:10.3969/j.issn.1005-202X.2026.09.005]
点击复制

基于双不确定性引导的抗噪半监督医学图像分割()

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
43卷
期数:
2026年第9期
页码:
1188-1195
栏目:
医学影像物理
出版日期:
2026-09-30

文章信息/Info

Title:
Noise-resilient semi-supervised medical image segmentation based on dual uncertainty guidance
文章编号:
1005-202X（2026）09-1188-08
作者:
黄贤泊; 程远志
青岛科技大学信息科学技术学院， 山东 青岛 266061
Author(s):
HUANG Xianbo;  CHENG Yuanzhi
College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China
关键词:
医学图像分割; 不确定性; 池化增强; 指数移动平均
Keywords:
Keywords: medical image segmentation uncertainty pooling enhancement exponential moving average
分类号:
R318；TP391.41
DOI:
DOI:10.3969/j.issn.1005-202X.2026.09.005
文献标志码:
A
摘要:
针对半监督医学图像分割中一致性正则化方法难以准确评估预测的可靠性且易受到噪声干扰的问题，提出一种基于双不确定性引导的抗噪半监督医学图像分割框架，联合评估模型自身的认知局限性与预测结果的解剖合理性。具体而言，设计基于残差指数移动平均的教师参数更新策略，有效减少师生模型参数偏差。其次，引入空间一致性增强的池化增强模块，抑制预测噪声并提升图像结构合理性；并融合双不确定性构建精准的权重分配机制，指导模型在无标注数据上的学习。在两个公共数据集上实验验证，LA数据集在10%标记数据的情况下，平均Dice和Jaccard系数分别达到88.61%和79.68%，BraTS2019数据集在20%标记数据的情况下，平均Dice和Jaccard系数分别达到84.27%和74.32%，证明方法的优越性。
Abstract:
Abstract: Given that consistency regularization methods in semi-supervised medical image segmentation struggle to accurately assess prediction reliability and are susceptible to noise, a noise-resilient semi-supervised medical image segmentation framework guided by dual uncertainty is developed to evaluate the inherent cognitive limitations of the model and the anatomical plausibility of its predictions. Specifically, a teacher parameter update strategy based on residual exponential moving average is designed to effectively reduce parameter deviation between the teacher and student models. Subsequently, a pooling enhancement module with spatial consistency reinforcement is introduced to suppress prediction noise and improve the structural rationality of the image. Furthermore, a precise weight allocation mechanism is constructed by integrating dual uncertainty to guide model learning on unlabeled data. Experiments on two public datasets shows that the proposed method ahcieves average Dice and Jaccard coefficients of 88.61% and 79.68% on the LA dataset with 10% labeled data, and 84.27% and 74.32% on the BraTS2019 dataset with 20% labeled data, demonstrating its superiority.

相似文献/References:

[1]万俊,聂生东,王远军,等.基于MRI的脑肿瘤分割技术研究进展[J].中国医学物理学杂志,2013,30(04):4266.[doi:10.3969/j.issn.1005-202X.2013.04.013]
[2]林江,戴齐,欧阳婷雪,等.一种边界和马尔可夫随机场相结合的脑MRI医学图像分割方法[J].中国医学物理学杂志,2015,32(05):717.[doi:doi:10.3969/j.issn.1005-202X.2015.05.023]
　[J].Chinese Journal of Medical Physics,2015,32(9):717.[doi:doi:10.3969/j.issn.1005-202X.2015.05.023]
[3]吴迪,胡胜,刘伟峰,等. 基于特征融合视觉显著性的医学图像分割[J].中国医学物理学杂志,2018,35(6):670.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.010]
　WU Di,HU Sheng,LIU Weifeng,et al. Medical image segmentation based on visual saliency of feature fusion[J].Chinese Journal of Medical Physics,2018,35(9):670.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.010]
[4]刘国才,官文静,田娟秀,等. 集成自适应回归核的肿瘤生物靶区随机游走勾画方法[J].中国医学物理学杂志,2018,35(7):758.[doi:DOI:10.3969/j.issn.1005-202X.2018.07.004]
　LIU Guocai,GUAN Wenjing,TIAN Juanxiu,et al. A random walk method with adaptive regression-kernel for delineation of biological target volumes of tumors[J].Chinese Journal of Medical Physics,2018,35(9):758.[doi:DOI:10.3969/j.issn.1005-202X.2018.07.004]
[5]宫进昌,赵尚义,王远军. 基于深度学习的医学图像分割研究进展[J].中国医学物理学杂志,2019,36(4):420.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.010]
　GONG Jinchang,ZHAO Shangyi,WANG Yuanjun.Research progress on deep learning-based medical image segmentation[J].Chinese Journal of Medical Physics,2019,36(9):420.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.010]
[6]张富利,杨安宁,路娜,等.基于FC_DenseNet深度学习网络自动分割肺癌放疗中的危及器官[J].中国医学物理学杂志,2021,38(2):259.[doi:DOI:10.3969/j.issn.1005-202X.2021.02.024]
　ZHANG Fuli,YANG Anning,LU Na,et al.FC_Densenet-based autosegmentation of organs-at-risk in lung cancer radiotherapy[J].Chinese Journal of Medical Physics,2021,38(9):259.[doi:DOI:10.3969/j.issn.1005-202X.2021.02.024]
[7]方新林,方艳红,王迪.基于多模态特征融合的脑瘤图像分割方法[J].中国医学物理学杂志,2022,39(6):682.[doi:DOI:10.3969/j.issn.1005-202X.2022.06.005]
　FANG Xinlin,FANG Yanhong,WANG Di.Brain tumor image segmentation method based on multi-modal feature fusion[J].Chinese Journal of Medical Physics,2022,39(9):682.[doi:DOI:10.3969/j.issn.1005-202X.2022.06.005]
[8]魏坤,沈记全,赵艳梅.MAUNet：用于皮肤病变分割的轻量级模型[J].中国医学物理学杂志,2023,40(5):555.[doi:DOI:10.3969/j.issn.1005-202X.2023.05.006]
　WEI Kun,SHEN Jiquan,ZHAO Yanmei.MAUNet: a lightweight model for skin lesion segmentation[J].Chinese Journal of Medical Physics,2023,40(9):555.[doi:DOI:10.3969/j.issn.1005-202X.2023.05.006]
[9]周金治,胡震,郭莉莉,等.基于GAN-DAUnet的肝脏CT图像肿瘤分割算法[J].中国医学物理学杂志,2023,40(8):971.[doi:DOI:10.3969/j.issn.1005-202X.2023.08.008]
　ZHOU Jinzhi,HU Zhen,et al.Liver CT image tumor segmentation algorithm based on GAN-DAUnet[J].Chinese Journal of Medical Physics,2023,40(9):971.[doi:DOI:10.3969/j.issn.1005-202X.2023.08.008]
[10]黄仟甲,张恒,李奇轩,等.医学图像分割的研究进展[J].中国医学物理学杂志,2024,41(8):939.[doi:DOI:10.3969/j.issn.1005-202X.2024.08.003]
　HUANG Qianjia,ZHANG Heng,,et al.Review on medical image segmentation methods[J].Chinese Journal of Medical Physics,2024,41(9):939.[doi:DOI:10.3969/j.issn.1005-202X.2024.08.003]

备注/Memo

备注/Memo:
【收稿日期】2026-04-18 【基金项目】山东省自然科学基金（ZR2025MS1009） 【作者简介】黄贤泊，硕士研究生，研究方向：医学图像处理，E-mail: 1745068167@qq.com 【通信作者】程远志，博士，教授，博士生导师，研究方向：计算机视觉、人工智能、大数据处理，E-mail: yzcheng2007@163.com
更新日期/Last Update: 2026-09-30