Mitosis detection for stem cell tracking in phase-contrast microscopy images

Abstract

Automated visual-tracking systems of stem cell populations in vitro allow for high-throughput analysis of time-lapse phase-contrast microscopy. In these systems, detection of mitosis, or cell division, is critical to tracking performance as mitosis causes branching of the trajectory of a mother cell into the two trajectories of its daughter cells. Recently, one mitosis detection algorithm showed its success in detecting the time and location that two daughter cells first clearly appear as a result of mitosis. This detection result can therefore helps trajectories to correctly bifurcate and the relations between mother and daughter cells to be revealed. In this paper, we demonstrate that the functionality of this recent mitosis detection algorithm significantly improves state-of-the-art cell tracking systems through extensive experiments on 48 C2C12 myoblastic stem cell populations under four different conditions.

Linking of Cell Tracks using Segmentation

“…To assess the calculation tests were performed on 115 picture groupings of Muscle Stem Cells (MuSCs) and the accuracy and review rate (called mitosis expanding rightness) registered by the calculation was seen to be to 0.78 and 0.75 for mitosis (cell division occasion) 0.74 and 0.62 for apoptosis (cell passing occasion), when contrasted with Huh et al [20] the review rate was 0.65. In light of a worldly probabilistic model a mechanized mitosis location calculation proposed by Huh et al [31] for approval of mitosis occasion recognition.…”

“…The have talked about on following cerebrum cells, as this strategy confirmations to get all around best arrangement. Huh et al [20] tells that following based strategy, following free technique are two writes in robotized mitosis discovery calculations. Following by closest neighbor approach, Park et al [21] examined on single mRNA following in live cells and received molecule computerized following of mRNA in cells Multiple Hypothesis Tracking (MHT) calculations and Kalman Filtering.…”

Global Linking of Cell Tracks Using the Viterbi Algorithm

“…It is therefore noteworthy that our algorithm produces good tracking results, and especially that mitotic events are identified with both high precision and high recall. In [27], mitotic events are handled using a mitosis detection algorithm specifically designed for phase-contrast microscopy [4]. Compared to the method used in [27], the proposed algorithm for handling of mitotic events has the advantages that it is independent of the microscopy technique used, and that it treats mitotic events in a probabilistic manner without making hard classification decisions before the tracking is started.…”

“…The biological questions can be extremely different from one another, but time-lapse microscopy is often a very important and powerful technique to study and analyze the cells [1]. Time-lapse microscopy can be used to characterize and quantify many different aspects of cell behavior, such as proliferation [2], mitosis (cell division) [3], [4], apoptosis (cell death) [5], migration [6], and morphology [7], that are important in the study of cancer [8], [9], embryogenesis [10], [11], stem cells [12]–[14], and many other topics in the fields of cell and developmental biology. In early works like [5], [10] cells were observed using transmission microscopy, and the images were sketched by hand at appropriate time intervals, or recorded on video tape in cases where all cells of interest were in the same focal plane.…”

A Novel Framework for Cellular Tracking and Mitosis Detection in Dense Phase Contrast Microscopy Images

“…Automatic cellular tracking is challenging due to several factors such as low image contrast, changes in the morphology of the cells over time, random migration, cell division [19], [27], [28], cell interaction [7] and low signal to noise ratio. These challenges vary to a great extent depending on the characteristics of the imaging systems or on the nature of the cell lines being analyzed, and as a result numerous semiautomatic [4]- [6] and fully automatic [1], [8], [11] cell tracking algorithms were proposed in the literature.…”