An organoid segmentation method incorporating wavelet scattering and capsule network
10.3969/j.issn.1005-202X.2025.04.003
- VernacularTitle:融合小波散射与胶囊网络的类器官图像分割方法
- Author:
Hongrui YANG
1
;
Gang LI
;
Zexin CHEN
;
Yujia ZHAI
;
Yingying XU
Author Information
1. 南方医科大学生物医学工程学院,广东 广州 510515;广东省医学图像处理重点实验室,广东 广州 510515;广东省医学成像与诊断技术工程实验室,广东 广州 510515
- Publication Type:Journal Article
- Keywords:
medical image segmentation;
organoid;
capsule network;
wavelet scattering network
- From:
Chinese Journal of Medical Physics
2025;42(4):435-442
- CountryChina
- Language:Chinese
-
Abstract:
Objective To develop and validate an automated organoid image segmentation approach based on deep learning for addressing the issues of high misidentification rate,blurred boundary and poor generalization in current organoid segmentation,thereby facilitating researchers to monitor and analyze organoid growth more efficiently.Methods The wavelet scattering coefficient matrix and capsule convolution module were integrated into the U-Net architecture to construct the organoid image segmentation model OrgCapsU-Net which was trained and evaluated on 3 organoid image datasets from different tissue sources.Results Compared with current mainstream segmentation algorithms,OrgCapsU-Net could better distinguish organoid and impurity,and lead to smoother segmentation boundaries,achieving superior performance across 4 evaluation metrics on 3 datasets.Conclusion OrgCapsU-Net delivers excellent segmentation performance and can be applied to organoids from various tissue sources,showing strong potential for applications in the in vitro model establishment,high-throughput drug screening,and personalized medicine.
