[1]杨红蕊,李刚,陈泽新,等.融合小波散射与胶囊网络的类器官图像分割方法[J].中国医学物理学杂志,2025,42(4):435-442.[doi:10.3969/j.issn.1005-202X.2025.04.003]
　YANG Hongrui,,et al.An organoid segmentation method incorporating wavelet scattering and capsule network[J].Chinese Journal of Medical Physics,2025,42(4):435-442.[doi:10.3969/j.issn.1005-202X.2025.04.003]
点击复制

融合小波散射与胶囊网络的类器官图像分割方法()
分享到：

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

卷:
42
期数:
2025年第4期
页码:
435-442
栏目:
医学影像物理
出版日期:
2025-04-20

文章信息/Info

Title:
An organoid segmentation method incorporating wavelet scattering and capsule network
文章编号:
1005-202X（2025）04-0435-08
作者:
杨红蕊 1; 2; 3; 李刚 4; 陈泽新 5; 翟羽佳 6; 7; 徐莹莹 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.南方医科大学南方医院惠侨医疗中心，广东 广州 510515；5.广东省类器官工程技术研究中心，广东 广州 510530；6. 广东医科大学附属医院肿瘤中心，广东 湛江 524001；7. 暨南大学药学院，广东 广州511436
Author(s):
YANG Hongrui1;  2;  3;  LI Gang4;  CHEN Zexin5;  ZHAI Yujia6;  7;  XU Yingying1;  2;  3
1. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; 2. Guangdong ProvincialKey Laboratory of Medical Image Processing, Guangzhou 510515, China; 3. Guangdong Provincial Engineering Laboratory forMedical Imaging and Diagnostic Technology, Guangzhou 510515, China; 4. Huiqiao Medical Center, Nanfang Hospital, SouthernMedical University, Guangzhou 510515, China; 5. Guangdong Research Center of Organoid Engineering and Technology, Guangzhou510530, China; 6. Cancer Center, Affiliated Hospital of Guangdong Medical University, Zhanjiang 524001, China; 7. College ofPharmacy, Ji’nan University, Guangzhou 511436, China
关键词:
医学影像分割; 类器官; 胶囊网络; 小波散射网络
Keywords:
medical image segmentation;  organoid;  capsule network;  wavelet scattering network
分类号:
R318；TP183
DOI:
10.3969/j.issn.1005-202X.2025.04.003
文献标志码:
A
摘要:
目的：构建并验证一种基于深度学习的类器官图像自动分割方法，旨在解决当前类器官分割中误识别率高、边界模糊、泛化性差的问题，以帮助研究人员更快更好地跟进和分析类器官细胞结构的生长情况。方法：在U-Net架构的基础上，引入小波散射系数矩阵与胶囊卷积模块，构建类器官图像分割模型OrgCapsU-Net，并在不同组织来源的3个类器官图像数据集上分别进行训练和测试。结果：与当前主流分割算法对比，OrgCapsU-Net能更好地区分类器官与杂质，分割边界也更加平滑，4个评估指标在3个数据集上均达到最优的结果。结论：OrgCapsU-Net实现良好的分割性能，能够适用于不同组织来源的类器官，在体外建模、高通量药物筛选以及个性化医疗方面具有较好的应用前景。
Abstract:
Objective To develop and validate an automated organoid image segmentation approach based on deep learningfor addressing the issues of high misidentification rate, blurred boundary and poor generalization in current organoidsegmentation, thereby facilitating researchers to monitor and analyze organoid growth more efficiently. Methods Thewavelet scattering coefficient matrix and capsule convolution module were integrated into the U-Net architecture to constructthe organoid image segmentation model OrgCapsU-Net which was trained and evaluated on 3 organoid image datasets fromdifferent tissue sources. Results Compared with current mainstream segmentation algorithms, OrgCapsU-Net could betterdistinguish organoid and impurity, and lead to smoother segmentation boundaries, achieving superior performance across 4evaluation metrics on 3 datasets. Conclusion OrgCapsU-Net delivers excellent segmentation performance and can be appliedto organoids from various tissue sources, showing strong potential for applications in the in vitro model establishment, highthroughput drug screening, and personalized medicine.

相似文献/References:

[1]刘 航,汪 冬,裴 曦,等.基于改进区域生长算法的肝脏分割方法研究[J].中国医学物理学杂志,2014,31(05):5204.[doi:10.3969/j.issn.1005-202X.2014.05.023]
[2]邓金城,彭应林,刘常春,等. 深度卷积神经网络在放射治疗计划图像分割中的应用[J].中国医学物理学杂志,2018,35(6):621.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.001]
　DENG Jincheng,PENG Yinglin,LIU Changchun,et al. Application of deep convolution neural network in radiotherapy planning image segmentation[J].Chinese Journal of Medical Physics,2018,35(4):621.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.001]
[3]徐凯成,方志军,蔡清萍,等.全局与局部注意力机制的胃部肿瘤分割算法[J].中国医学物理学杂志,2021,38(4):446.[doi:DOI:10.3969/j.issn.1005-202X.2021.04.010]
　XU Kaicheng,FANG Zhijun,CAI Qingping,et al.Gastric tumor segmentation algorithm based on global-local attention mechanism[J].Chinese Journal of Medical Physics,2021,38(4):446.[doi:DOI:10.3969/j.issn.1005-202X.2021.04.010]

备注/Memo

备注/Memo:
【收稿日期】2024-12-11【基金项目】国家自然科学基金（61803196）；广东省基础与应用基础研究基金（2020B1212060039，2022A1515011436）【作者简介】杨红蕊，硕士，研究方向：医学图像处理，E-mail: 1722758676@qq.com【通信作者】徐莹莹，副教授，研究方向：生物医学图像分析、生物信息学，E-mail: yyxu@smu.edu.cn
更新日期/Last Update: 2025-04-30