Search

Advances in time-lapse 3D in vivo fluorescence microscopic imaging techniques enables the observation and investigation into the migration of Oligodendrocyte precursor cells (OPCs) and its role in the central nervous system. However, current practice of image-based OPC motility analysis heavily relies on manual labeling and tracking on 2D max projection of the 3D data, which suffers from massive human labor, subjective biases, weak reproducibility and especially information loss and distortion. Besides, due to the lack of OPC specific genetically encoded indicator, OPCs can only be identified from other oligodendrocyte lineage cells by their observed motion patterns. Automated analytical tools are needed for the identification and tracking of OPCs. In this dissertation work, we proposed an analytical framework, MicTracker (Migrating Cell Tracker), for the integrated task of identifying, segmenting and tracking migrating cells (OPCs) from in vivo time-lapse fluorescence imaging data of high-density cell clusters composed of cells with different modes of motions. As a component of the framework, we presented a novel strategy for cell segmentation with global temporal consistency enforced, tackling the challenges caused by highly clustered cell population and temporally inconsistently blurred boundaries between touching cells. We also designed a data association algorithm to address the violation of usual assumption of small displacements. Recognizing that the violation was in the mixed cell population composed of two cell groups while the assumption held within each group, we proposed to solve the seemingly impossible mission by de-mixing the two groups of cell motion modes without known labels. We demonstrated the effectiveness of MicTracker in solving our problem on in vivo real data. Doctor of Philosophy Oligodendrocyte precursor cells (OPCs) are a type of motile cells in the central nervous system (CNS). OPCs' migration plays a critical role in the repair and re-distribution of myelin sheaths, a structures that helps to accelerate the transmission of electrical signals from neuron to neuron. But the mechanism behind the motility of OPCs is largely unclear. In recent years, advances in genetic fluorescence indicators and time-lapse optical microscopic imaging techniques, especially 3D in vivo imaging, enables neuroscientists to investigate into the puzzle. However, current practice of OPC motility analysis heavily relies on compressing the 3D data into 2D then manually tracking the OPCs, which suffers from not only massive human labor, subjective biases, weak reproducibility and especially information loss and distortion. Automated analytical tools are needed. Due to the limitation of current techniques in fluorescent labeling of cells in live animals, OPCs cannot be distinctively labeled. Instead, in the field of view there are also other irrelevant cells that cannot migrate but locally vibrate. Therefore, the human analyzer or the analytical software is supposed to detect OPCs from a cluster of touching cells containing multiple types of cells by their motion patterns only. In this dissertation, we presented a fully automatic machine learning based algorithm, MicTracker (Migrating Cell Tracker), to identify and track migrating OPCs. The task cannot be straightforwardly solved by existing generic-purpose cell tracking tools due to quite a few special challenges. To tackle the challenges, we also proposed novel methods for two major modules of MicTracker, segmentation and linking, respectively. We demonstrated the effectiveness of MicTracker and its components on real data and compared it with related existing works. The results of experiments showed notable superiority of MicTracker in solving our problem, compared with existing methods.