Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering.

Lee-Ling Sharon Ong,Mengmeng Wang,Justin Dauwels,H Harry Asada

doi:10.1117/1.jmi.5.2.024005

Abstract

.Cell migration is a key feature for living organisms. Image analysis tools are useful in studying cell migration in three-dimensional (3-D) in vitro environments. We consider angiogenic vessels formed in 3-D microfluidic devices (MFDs) and develop an image analysis system to extract cell behaviors from experimental phase-contrast microscopy image sequences. The proposed system initializes tracks with the end-point confocal nuclei coordinates. We apply convolutional neural networks to detect cell candidates and combine backward Kalman filtering with multiple hypothesis tracking to link the cell candidates at each time step. These hypotheses incorporate prior knowledge on vessel formation and cell proliferation rates. The association accuracy reaches 86.4% for the proposed algorithm, indicating that the proposed system is able to associate cells more accurately than existing approaches. Cell culture experiments in 3-D MFDs have shown considerable promise for improving biology research. The proposed system is expected to be a useful quantitative tool for potential microscopy problems of MFDs.

Highlights

Cell migration experiments can be performed in three-dimensional (3-D) microfluidic devices (MFDs).[1]
We focus on tracking by detection algorithm to track the migrating endothelial cells (ECs) within angiogenic vessels formed in 3-D MFDs by linking the coarse time-lapse 2-D phase-contrast images and 3-D end-point confocal images
We presented an automated image analysis system to track the migrating ECs within 3-D angiogenic vessels cultured in MFDs by combining end-point confocal and time-lapse phase-contrast

Summary

Introduction

Cell migration experiments can be performed in three-dimensional (3-D) microfluidic devices (MFDs).[1] These devices, with channels allowing either fluid to flow or gel scaffolds to be injected, mimic the in vivo environments. In conventional two-dimensional (2-D) in vitro experiments, cells move freely and form a thin layer rather than a structure. We can only see the formed structure. From the experiments in the 3-D MFDs, we can obtain the microscopy images of both the structure and the individual cells. As controlled reactions can be reproduced with a small volume of samples and reagents, MFDs are used for long-term studies of many biological processes. We consider cell migration during angiogenesis and develop an automated image analysis system to extract cell migration behaviors

Objectives

Results

Conclusion