[1]陈翔,张桢泰,龙楷兴,等.肾小球超微结构的半监督语义分割方法[J].中国医学物理学杂志,2025,42(6):757-765.[doi:DOI:10.3969/j.issn.1005-202X.2025.06.008]
　CHEN Xiang,,et al.Semi-supervised semantic segmentation method for glomerular ultrastructure[J].Chinese Journal of Medical Physics,2025,42(6):757-765.[doi:DOI:10.3969/j.issn.1005-202X.2025.06.008]
点击复制

肾小球超微结构的半监督语义分割方法()

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

卷:
42
期数:
2025年第6期
页码:
757-765
栏目:
医学影像物理
出版日期:
2025-06-20

文章信息/Info

Title:
Semi-supervised semantic segmentation method for glomerular ultrastructure
文章编号:
1005-202X（2025）06-0757-09
作者:
陈翔1; 2; 3; 张桢泰1; 2; 3; 龙楷兴1; 2; 3; 路艳蒙4; 耿舰5; 6; 周志涛4; 曹蕾1; 2; 3
1.南方医科大学生物医学工程学院，广东 广州 510515；2.广东省医学图像处理重点实验室，广东 广州 510515；3.广东省医学成像与诊断技术工程实验室，广东 广州 510515；4.南方医科大学中心实验室，广东 广州 510515；5.南方医科大学基础医学院，广东 广州 510515；6.广州华银医学检验中心，广东 广州 510515
Author(s):
CHEN Xiang1;  2;  3;  ZHANG Zhentai1;  2;  3;  LONG Kaixing1;  2;  3;  LU Yanmeng4;  GENG Jian5;  6;  ZHOU Zhitao4;  CAO Lei1;  2;  3
1. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; 2. Guangdong Provincial KeyLaboratory of Medical Image Processing, Guangzhou 510515, China; 3. Guangdong Provincial Engineering Laboratory for MedicalImaging and Diagnostic Technology, Guangzhou 510515, China; 4. Central Laboratory, Southern Medical University, Guangzhou510515, China; 5. School of Basic Medical Sciences, Southern Medical University, Guangzhou 510515, China; 6. Guangzhou HuayinMedical Laboratory Center, Guangzhou 510515, China
关键词:
医学图像分割; 半监督学习; 一致性正则化; 肾小球超微结构
Keywords:
medical image segmentation;  semi-supervised learning;  consistency regularization;  glomerular ultrastructure
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2025.06.008
文献标志码:
A
摘要:
肾小球超微结构的精准识别对慢性肾脏病诊断至关重要，但高质量标注数据的获取成本限制了全监督学习的应用。为此，提出一种基于SAM（Segment Anything Model）的多类别半监督语义分割框架MC4S-SAM。首先，对SAM的掩码解码器进行改进，使其在无需提示信息的情况下具备多类别语义分割能力；然后，利用改进后的模型通过自训练（Self-training）策略生成并优化伪标签；最后，构建多级一致性正则化约束提升模型性能。实验结果表明，在肾小球系膜区超微结构分割任务中，使用DeepLabV3+作为分割网络，MC4S-SAM在标注数据量占比为1/16时，平均交并比（mIoU）和平均Dice系数（mDSC）分别比全监督模型提高11.72%和11.45%；在标注数据量占比为1/4时，其mIoU和mDSC分别达到68.91%和78.73%，为慢性肾脏病的辅助诊断提供重要的应用价值。
Abstract:
Accurate identification of the glomerular ultrastructure is critical for the diagnosis of chronic kidney diseases, butthe high cost of acquiring high-quality annotated data limits the application of fully-supervised learning. Therefore, a multi-classsemi-supervised semantic segmentation framework based on segment anything model (MC4S-SAM) is proposed. Afterimproving the mask decoder of segment anything model to enable multi-class semantic segmentation without requiringprompt information, the improved model is used to generate and refine pseudo-labels through a self-training strategy, andmulti-level consistency regularization constraints are incorporated to enhance the model’s performance. Experimental resultsshow that, in the task of segmenting the glomerular mesangial ultrastructure, MC4S-SAM outperformes the fully-supervisedmodel by 11.72% in mean intersection over union (mIoU) and 11.45% in mean Dice similarity coefficient (mDSC) when thelabeled data accountes for 1/16 of the total. When the labeled data proportion is 1/4, the mIoU and mDSC reach 68.91% and78.73%, respectively, demonstrating its significant potential for aiding the diagnosis of chronic kidney diseases.

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(6):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(6):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(6):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(6):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(6):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(6):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(6):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(6):971.[doi:DOI:10.3969/j.issn.1005-202X.2023.08.008]
[10]段逸凡,肖洪兵,Rahman Md Mostafizur.基于3DSEU-Net不确定性循环焦点平均教师的半监督脑肿瘤分割[J].中国医学物理学杂志,2023,40(9):1121.[doi:DOI:10.3969/j.issn.1005-202X.2023.09.010]
　DUAN Yifan,XIAO Hongbing,Rahman Md Mostafizur.Semi-supervised learning for brain tumor segmentation through 3DSEU-Net as uncertainty-aware mean teacher and cyclical focal loss[J].Chinese Journal of Medical Physics,2023,40(6):1121.[doi:DOI:10.3969/j.issn.1005-202X.2023.09.010]
[11]刘卫朋,祁业东,李健,等.基于多尺度区域可靠性感知的半监督肺肿瘤分割[J].中国医学物理学杂志,2024,41(9):1078.[doi:DOI:10.3969/j.issn.1005-202X.2024.09.004]
　LIU Weipeng,QI Yedong,et al.Semi-supervised lung tumor segmentation based on multi-scale consistency and regional reliability perception[J].Chinese Journal of Medical Physics,2024,41(6):1078.[doi:DOI:10.3969/j.issn.1005-202X.2024.09.004]

备注/Memo

备注/Memo:
【收稿日期】2025-01-18【基金项目】国家自然科学基金（32071368）【作者简介】陈翔，硕士研究生，研究方向：医学图像分割，E-mail:qluchenxiang@163.com【通信作者】曹蕾，博士，副教授，研究方向：医学图像分析，E-mail:caolei@smu.edu.cn
更新日期/Last Update: 2025-06-30