A Method for Automatic Tracking of Cell Nuclei in 2D Epifluorescence Microscopy Image Sequences
A Method for Automatic Tracking of Cell Nuclei in 2D Epifluorescence Microscopy Image Sequences
复制标题
二维落射荧光显微镜图像序列中细胞核自动跟踪的方法
DOI：
10.1109/ipta.2018.8608156
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Sorokin Dmitry V.
中科院分区：
文献类型：
--
作者：
Kondratiev Alexandr Yu.;Yaginuma Hideyuki;Okada Yasushi;Sorokin Dmitry V.
活细胞显微图像序列中细胞的自动分割和跟踪是许多生物学研究领域的实际问题。尽管存在不同的细胞跟踪方法，但由于使用不同技术获得的荧光显微镜图像数据种类繁多，其中细胞具有完全不同的视觉外观，因此仍然不存在针对该问题的通用解决方案。此外，即使在单个图像序列中，细胞也可以显著改变其形状。在这项工作中，我们提出了一种细胞跟踪算法，设计用于检测和跟踪细胞核在二维图像序列中获得的落射荧光显微镜，其中细胞的外观急剧变化，在细胞有丝分裂。我们使用标记控制的分水岭算法结合斑点检测的细胞核分割，其次是一个广义的最近邻核跟踪方法。我们还采用了一种特殊的有丝分裂检测算法来处理细胞分裂事件。我们的方法进行了定量评估，其分割和跟踪精度使用人类专家注释的真实的图像数据。根据细胞追踪挑战中使用的方案进行评价程序。结果表明，该方法优于现有的半自动方法在分割和跟踪精度。
The automated segmentation and tracking of cells in live cell microscopy image sequences is an actual problem in many biological research areas. Despite the existence of different cell tracking approaches, a universal solution for this problem still does not exist due to high variety of fluorescent microscopy image data obtained using different techniques, where cells have completely different visual appearance. Moreover, the cells can significantly change their shape even within a single image sequence. In this work, we propose a cell tracking algorithm designed for detecting and tracking cell nuclei in 2D image sequences obtained by epifluorescence microscopy, where the cell appearance drastically changes during cell mitosis. We used marker controlled watershed algorithm combined with blob detection for nuclei segmentation followed by a generalized nearest neighbor approach for nuclei tracking. We also employed a special mitosis detection algorithm to process cell division events. Our approach was quantitatively evaluated for its segmentation and tracking accuracy using the real image data annotated by human experts. The evaluation procedure was performed based on the protocol used in the Cell Tracking Challenge. It was shown that the proposed approach outperforms an existing semiautomatic method in both segmentation and tracking accuracy.