IEEE/ACM Trans Comput Biol Bioinform. 2021 Sep-Oct;18(5):1850-1863. doi: 10.1109/TCBB.2019.2954502. Epub 2021 Oct 7.
In this article, we take as inspiration the labor division into scouts and workers in an ant colony and propose a novel approach for automated cell tracking in the framework of multi-Bernoulli random finite sets. To approximate the Bernoulli parameter sets, we first define an existence probability of an ant colony as well as its discrete density distribution. During foraging, the behavior of scouts is modeled as a chaotic movement to produce a set of potential candidates. Afterwards, a group of workers, i.e., a worker ant colony, is recruited for each candidate, which then embark on gathering heuristic information in a self-organized way. Finally, the pheromone field is formed by the corresponding worker ant colony, from which the Bernoulli parameter is derived and the state of the cell is estimated accordingly to be associated with the existing tracks. Performance comparisons with other previous approaches are conducted on both simulated and real cell image sequences and show the superiority of this algorithm.
在本文中，我们受到蚁群中侦察兵和工人分工的启发，在多伯努利随机有限集框架下提出了一种新的自动细胞跟踪方法。为了逼近伯努利参数集，我们首先定义了蚁群的存在概率及其离散密度分布。在觅食过程中，侦察兵的行为被建模为一种混沌运动，以产生一组潜在的候选者。然后，为每个候选者招募一组工人，即一个工蚁群，然后它们以自组织的方式收集启发式信息。最后，由相应的工蚁群形成信息素场，从中得出伯努利参数，并根据该参数估计细胞的状态，以与现有轨迹相关联。我们在模拟和真实细胞图像序列上对该方法与其他先前方法进行了性能比较，结果表明了该算法的优越性。
