期刊
2021 IEEE 18TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI)
卷 -, 期 -, 页码 385-389出版社
IEEE
DOI: 10.1109/ISBI48211.2021.9433831
关键词
nuclei; cell; supervoxel; boundary; 3D UNet; segmentation; tracking; watershed; graph
资金
- National Science Foundation (NSF) [1664172]
- Direct For Computer & Info Scie & Enginr [1664172] Funding Source: National Science Foundation
- Office of Advanced Cyberinfrastructure (OAC) [1664172] Funding Source: National Science Foundation
The study introduces a novel weakly supervised method to enhance the boundary of 3D segmented nuclei using over-segmented images, combining a 3D U-Net for nuclei centroid extraction and a simple linear iterative clustering algorithm for better cluster boundary adherence. The algorithm utilizes relative nuclei location to track the segmented nuclei, achieving improved segmentation performance compared to previous methods in Cell Tracking Challenge (CTC) 2019 and comparable performance to state-of-the-art methods in IEEE ISBI CTC2020 with minimal pixel-wise annotated data.
We propose a novel weakly supervised method to improve the boundary of the 3D segmented nuclei utilizing an over-segmented image. This is motivated by the observation that current state-of-the-art deep learning methods do not result in accurate boundaries when the training data is weakly annotated. Towards this, a 3D U-Net is trained to get the centroid of the nuclei and integrated with a simple linear iterative clustering (SLIC) supervoxel algorithm that provides better adherence to cluster boundaries. To track these segmented nuclei, our algorithm utilizes the relative nuclei location depicting the processes of nuclei division and apoptosis. The proposed algorithmic pipeline achieves better segmentation performance compared to the state-of-the-art method in Cell Tracking Challenge (CTC) 2019 and comparable performance to state-of-the-art methods in IEEE ISBI CTC2020 while utilizing very few pixel-wise annotated data. Detailed experimental results are provided, and the source code is available on (1)GitHub.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据