Advanced Level-Set-Based Cell Tracking in Time-Lapse Fluorescence Microscopy
Advanced Level-Set-Based Cell Tracking in Time-Lapse Fluorescence Microscopy
复制标题
DOI：
10.1109/tmi.2009.2038693
复制
发表时间：
2010-03-01
影响因子：
10.6
通讯作者：
Meijering, Erik
中科院分区：
文献类型：
--
作者：
Dzyubachyk, Oleh;van Cappellen, Wiggert A.;Meijering, Erik
延时荧光显微镜图像中的细胞分割和跟踪是在许多关于细胞迁移和增殖的生物学研究中至关重要的任务。近年来，已经证明水平集为此目的提供了非常合适的框架，因为它们非常适合捕获有丝分裂过程中发生的拓扑变化，并且它们很容易扩展到更高的维图像数据。该模型进化方法也已扩展以同时处理许多细胞。尽管具有高潜力，但多层基准的方法遭受了许多缺点，这将其适用性限制在各种细胞生物成像研究中。在本文中，我们提出了对耦合 - 曲面算法的几种修改和扩展，这些算法大大提高了其鲁棒性和适用性。我们的算法通过将其与原始算法和其他两种细胞分割算法进行比较来验证。为了进行评估，使用了四个真实的荧光显微镜图像数据集，涉及代表大量生物学实验的不同细胞类型和标记。从精度（最高11％），召回（高达8％），正确捕获所有细胞分裂事件的能力以及计算时间（减少9次）方面，跟踪性能的提高。
Cell segmentation and tracking in time-lapse fluorescence microscopy images is a task of fundamental importance in many biological studies on cell migration and proliferation. In recent years, level sets have been shown to provide a very appropriate framework for this purpose, as they are well suited to capture topological changes occurring during mitosis, and they easily extend to higher dimensional image data. This model evolution approach has also been extended to deal with many cells concurrently. Notwithstanding its high potential, the multiple-level-set method suffers from a number of shortcomings, which limit its applicability to a larger variety of cell biological imaging studies. In this paper, we propose several modifications and extensions to the coupled-active-surfaces algorithm, which considerably improve its robustness and applicability. Our algorithm was validated by comparing it to the original algorithm and two other cell segmentation algorithms. For the evaluation, four real fluorescence microscopy image datasets were used, involving different cell types and labelings that are representative of a large range of biological experiments. Improved tracking performance in terms of precision (up to 11%), recall (up to 8%), ability to correctly capture all cell division events, and computation time (up to nine times reduction) is achieved.