Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering
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 f...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2018
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/87775 http://hdl.handle.net/10220/45505 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-87775 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-877752021-01-10T11:47:36Z Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering Ong, Sharon Lee-Ling Dauwels, Justin Asada, H. Harry Wang, Mengmeng School of Electrical and Electronic Engineering Singapore-MIT Alliance Programme Energy Research Institute @ NTU (ERI@N) Backward Kalman Filters Coarse Time-lapse Phase-contrast Images 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. NRF (Natl Research Foundation, S’pore) Published version 2018-08-07T04:34:36Z 2019-12-06T16:49:15Z 2018-08-07T04:34:36Z 2019-12-06T16:49:15Z 2018 Journal Article Wang, M., Ong, S. L.-L., Dauwels, J., & Asada, H. H. (2018). Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering. Journal of Medical Imaging, 5(02), 024005-. 2329-4302 https://hdl.handle.net/10356/87775 http://hdl.handle.net/10220/45505 10.1117/1.JMI.5.2.024005 en Journal of Medical Imaging © 2018 The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. 13 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Backward Kalman Filters Coarse Time-lapse Phase-contrast Images |
spellingShingle |
Backward Kalman Filters Coarse Time-lapse Phase-contrast Images Ong, Sharon Lee-Ling Dauwels, Justin Asada, H. Harry Wang, Mengmeng Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering |
description |
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. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Ong, Sharon Lee-Ling Dauwels, Justin Asada, H. Harry Wang, Mengmeng |
format |
Article |
author |
Ong, Sharon Lee-Ling Dauwels, Justin Asada, H. Harry Wang, Mengmeng |
author_sort |
Ong, Sharon Lee-Ling |
title |
Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering |
title_short |
Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering |
title_full |
Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering |
title_fullStr |
Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering |
title_full_unstemmed |
Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering |
title_sort |
multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented bayesian filtering |
publishDate |
2018 |
url |
https://hdl.handle.net/10356/87775 http://hdl.handle.net/10220/45505 |
_version_ |
1690658360144166912 |