DeepSea is an efficient deep-learning model for single-cell segmentation and tracking in time-lapse microscopy.
DeepSea is an efficient deep-learning model for single-cell segmentation and tracking in time-lapse microscopy.
复制标题
DOI：
10.1016/j.crmeth.2023.100500
复制
发表时间：
2023-06-26
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
时间推移显微镜是唯一一种可以在单细胞水平上以高时间分辨率直接捕捉基本细胞过程的动力学和异质性的方法。单细胞延时显微镜的成功应用需要在几个时间点上自动分割和跟踪数百个单个细胞。然而，单个细胞的分割和跟踪对于时间推移显微镜图像的分析仍然具有挑战性，特别是对于广泛使用的和无毒的成像方式，例如相位对比成像。这项工作提出了一个通用的、可训练的深度学习模型，称为DeepSea，它允许以比现有模型更高的精度分割和跟踪相衬活体显微镜图像序列中的单个细胞。我们通过分析胚胎干细胞中细胞大小的调节来展示DeepSea的应用。DeepSEA是一个用于细胞分割和跟踪的深度学习模型DeepSea软件是一个用户友好的工具，用于活显微镜的定量分析DeepSea可以准确地分割和跟踪不同类型的单细胞DeepSea可以很容易地训练来分割和跟踪新的细胞类型延时显微镜允许在单细胞水平上以高时间分辨率直接观察细胞的生物过程。单细胞时间推移显微镜的定量分析需要在几天内自动分割和跟踪单个细胞。精确的分割和跟踪仍然具有挑战性，因为细胞会改变形状、分裂并显示不可预测的运动。这项工作的动机是应用深度学习模型分析显微镜图像的最新进展。我们提出了一个基于深度学习的模型和一个用户友好的软件，称为DeepSea，用于自动分割和跟踪时间推移显微镜图像中的单个细胞。我们通过监测干细胞在细胞周期中的大小来展示我们的软件的应用。Zargari等人。开发一种深度学习模型来检测单个细胞，并随着时间的推移在活显微镜图像中跟踪它们。用户友好的DeepSea软件使研究人员能够在单细胞水平上提取有关细胞生物学过程动力学的定量信息。
Time-lapse microscopy is the only method that can directly capture the dynamics and heterogeneity of fundamental cellular processes at the single-cell level with high temporal resolution. Successful application of single-cell time-lapse microscopy requires automated segmentation and tracking of hundreds of individual cells over several time points. However, segmentation and tracking of single cells remain challenging for the analysis of time-lapse microscopy images, in particular for widely available and non-toxic imaging modalities such as phase-contrast imaging. This work presents a versatile and trainable deep-learning model, termed DeepSea, that allows for both segmentation and tracking of single cells in sequences of phase-contrast live microscopy images with higher precision than existing models. We showcase the application of DeepSea by analyzing cell size regulation in embryonic stem cells. DeepSea is a deep-learning model for cell segmentation and tracking DeepSea software is a user-friendly tool for quantitative analysis of live microscopy DeepSea can accurately segment and track different types of single cells DeepSea can be easily trained to segment and track new cell types Time-lapse microscopy allows for direct observation of cell biological processes at the single-cell level with high temporal resolution. Quantitative analysis of single-cell time-lapse microscopy requires automated segmentation and tracking of individual cells over several days. Precise segmentation and tracking remain challenging because cells change their shape, divide, and show unpredictable movements. This work is motivated by recent advances in the application of deep-learning models for the analysis of microscopy images. We present a deep-learning-based model and a user-friendly software, termed DeepSea, to automate both the segmentation and tracking of individual cells in time-lapse microscopy images. We showcase the application of our software by monitoring the size of the stem cells as cells progress through the cell cycle. Zargari et al. develop a deep-learning model to detect individual cells and track them over time in live microscopy images. The user-friendly DeepSea software allows researchers to extract quantitative information about dynamics of cell biological processes at the single-cell level.