Schiegg Martin, Hanslovsky Philipp, Haubold Carsten, Koethe Ullrich, Hufnagel Lars, Hamprecht Fred A
University of Heidelberg, IWR/HCI, 69115 Heidelberg, Germany and European Molecular Biology Laboratory (EMBL), Cell Biology and Biophysics Unit, 69117 Heidelberg, Germany.
Bioinformatics. 2015 Mar 15;31(6):948-56. doi: 10.1093/bioinformatics/btu764. Epub 2014 Nov 17.
To gain fundamental insight into the development of embryos, biologists seek to understand the fate of each and every embryonic cell. For the generation of cell tracks in embryogenesis, so-called tracking-by-assignment methods are flexible approaches. However, as every two-stage approach, they suffer from irrevocable errors propagated from the first stage to the second stage, here from segmentation to tracking. It is therefore desirable to model segmentation and tracking in a joint holistic assignment framework allowing the two stages to maximally benefit from each other.
We propose a probabilistic graphical model, which both automatically selects the best segments from a time series of oversegmented images/volumes and links them across time. This is realized by introducing intra-frame and inter-frame constraints between conflicting segmentation and tracking hypotheses while at the same time allowing for cell division. We show the efficiency of our algorithm on a challenging 3D+t cell tracking dataset from Drosophila embryogenesis and on a 2D+t dataset of proliferating cells in a dense population with frequent overlaps. On the latter, we achieve results significantly better than state-of-the-art tracking methods.
Source code and the 3D+t Drosophila dataset along with our manual annotations will be freely available on http://hci.iwr.uni-heidelberg.de/MIP/Research/tracking/
为了深入了解胚胎发育的基本过程，生物学家试图了解每个胚胎细胞的命运。对于胚胎发育过程中细胞轨迹的生成，所谓的分配跟踪方法是灵活的途径。然而，作为每一种两阶段方法，它们都存在从第一阶段传播到第二阶段的不可挽回的错误，在这里是从分割到跟踪。因此，期望在联合整体分配框架中对分割和跟踪进行建模，使两个阶段能够最大限度地相互受益。
我们提出了一种概率图形模型，它既能从过度分割的图像/体积的时间序列中自动选择最佳片段，又能跨时间将它们链接起来。这是通过在相互冲突的分割和跟踪假设之间引入帧内和帧间约束来实现的，同时允许细胞分裂。我们在来自果蝇胚胎发育的具有挑战性的3D+t细胞跟踪数据集以及密集群体中具有频繁重叠的增殖细胞的2D+t数据集上展示了我们算法的效率。在后者上，我们取得的结果明显优于当前最先进的跟踪方法。
源代码以及3D+t果蝇数据集连同我们的手动注释将在http://hci.iwr.uni-heidelberg.de/MIP/Research/tracking/上免费提供。
