Protocol for live cell image segmentation to profile cellular morphodynamics using MARS-Net.

Protocol for live cell image segmentation to profile cellular morphodynamics using MARS-Net.
复制标题

DOI:
10.1016/j.xpro.2022.101469
复制
发表时间:
2022-09-16
期刊:
影响因子:
--
通讯作者:
--
中科院分区:
其他
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

细胞形态动力学的定量研究依赖于活细胞图像中准确的细胞分割。然而,荧光和相衬成像阻碍准确的边缘定位。为了应对这一挑战,我们开发了MARS-Net,这是一种深度学习模型,集成了ImageNet预训练的VGG 19编码器和U-Net解码器,这些解码器是在多种类型的显微图像数据集上训练的。在这里,我们提供了安装MARS-Net,标记图像,训练MARS-Net进行边缘定位,评估训练模型的性能以及进行细胞形态动力学定量分析的协议。有关本方案使用和执行的完整详细信息,请参阅。基于深度学习的活细胞电影分割流水线用于地面真实掩模的半自动标记工具训练分割模型并评估其分割准确性从检测到的细胞边缘定量细胞形态动力学出版商说明:进行任何实验方案都需要遵守实验室安全和伦理的当地机构指南。细胞形态动力学的定量研究依赖于活细胞图像中准确的细胞分割。然而,荧光和相衬成像阻碍准确的边缘定位。为了应对这一挑战,我们开发了MARS-Net,这是一种深度学习模型,集成了ImageNet预训练的VGG 19编码器和U-Net解码器,这些解码器是在多种类型的显微图像数据集上训练的。在这里,我们提供了安装MARS-Net,标记图像,训练MARS-Net进行边缘定位,评估训练模型的性能以及进行细胞形态动力学定量分析的协议。
Quantitative studies of cellular morphodynamics rely on accurate cell segmentation in live cell images. However, fluorescence and phase contrast imaging hinder accurate edge localization. To address this challenge, we developed MARS-Net, a deep learning model integrating ImageNet-pretrained VGG19 encoder and U-Net decoder trained on the datasets from multiple types of microscopy images. Here, we provide the protocol for installing MARS-Net, labeling images, training MARS-Net for edge localization, evaluating the trained models’ performance, and performing the quantitative profiling of cellular morphodynamics. For complete details on the use and execution of this protocol, please refer to. Deep learning-based segmentation pipeline for live cell movies Semi-automatic labeling tool for ground truth masks Train segmentation models and evaluate their segmentation accuracy Quantification of cellular morphodynamics from detected cell edges Publisher’s note: Undertaking any experimental protocol requires adherence to local institutional guidelines for laboratory safety and ethics. Quantitative studies of cellular morphodynamics rely on accurate cell segmentation in live cell images. However, fluorescence and phase contrast imaging hinder accurate edge localization. To address this challenge, we developed MARS-Net, a deep learning model integrating ImageNet-pretrained VGG19 encoder and U-Net decoder trained on the datasets from multiple types of microscopy images. Here, we provide the protocol for installing MARS-Net, labeling images, training MARS-Net for edge localization, evaluating the trained models’ performance, and performing the quantitative profiling of cellular morphodynamics.
DOI: 10.1038/nature08242
发表时间: 2009-09-03
期刊: Nature
影响因子: 64.8
作者:
通讯作者: --
DOI: 10.1016/j.crmeth.2021.100105
发表时间: 2021-11-22
期刊: CELL REPORTS METHODS
影响因子: --
作者:
Jang, Junbong;Wang, Chuangqi;Lee, Kwonmoo
通讯作者: Lee, Kwonmoo
DOI: 10.1038/s41467-018-04030-0
发表时间: 2018-04-27
影响因子: 16.6
作者:
Wang C;Choi HJ;Kim SJ;Desai A;Lee N;Kim D;Bae Y;Lee K
通讯作者: Lee K
DOI: 10.1038/s41598-021-02683-4
发表时间: 2021-12-02
期刊: Scientific reports
影响因子: 4.6
作者:
Vaidyanathan K;Wang C;Krajnik A;Yu Y;Choi M;Lin B;Jang J;Heo SJ;Kolega J;Lee K;Bae Y
通讯作者: Bae Y
DOI: 10.1109/tpami.1986.4767851
发表时间: 1986-11-01
影响因子: 23.6
作者:
CANNY, J
通讯作者: CANNY, J