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...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
SPIE
2018
|
| Online Access: | http://hdl.handle.net/1721.1/118771 https://orcid.org/0000-0003-3155-6223 |
| _version_ | 1811083059671334912 |
|---|---|
| author | Wang, Mengmeng Ong, Lee-Ling Sharon Dauwels, Justin Asada, Haruhiko |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Wang, Mengmeng Ong, Lee-Ling Sharon Dauwels, Justin Asada, Haruhiko |
| author_sort | Wang, Mengmeng |
| collection | MIT |
| 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. |
| first_indexed | 2024-09-23T12:19:32Z |
| format | Article |
| id | mit-1721.1/118771 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T12:19:32Z |
| publishDate | 2018 |
| publisher | SPIE |
| record_format | dspace |
| spelling | mit-1721.1/1187712022-09-28T01:02:38Z Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering Wang, Mengmeng Ong, Lee-Ling Sharon Dauwels, Justin Asada, Haruhiko Massachusetts Institute of Technology. Department of Mechanical Engineering Asada, Haruhiko 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. 2018-10-25T15:28:29Z 2018-10-25T15:28:29Z 2018-06 2018-02 2018-10-25T13:33:15Z Article http://purl.org/eprint/type/ConferencePaper 2329-4302 2329-4310 http://hdl.handle.net/1721.1/118771 Wang, Mengmeng et al. “Multicell Migration Tracking Within Angiogenic Networks by Deep Learning-Based Segmentation and Augmented Bayesian Filtering.” Journal of Medical Imaging 5, 2 (June 2018): 024005 © 2018 The Authors https://orcid.org/0000-0003-3155-6223 http://dx.doi.org/10.1117/1.JMI.5.2.024005 Journal of Medical Imaging Creative Commons Attribution 3.0 Unported license http://creativecommons.org/licenses/by/3.0/ application/pdf SPIE SPIE |
| spellingShingle | Wang, Mengmeng Ong, Lee-Ling Sharon Dauwels, Justin Asada, Haruhiko Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering |
| title | 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_short | 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 |
| url | http://hdl.handle.net/1721.1/118771 https://orcid.org/0000-0003-3155-6223 |
| work_keys_str_mv | AT wangmengmeng multicellmigrationtrackingwithinangiogenicnetworksbydeeplearningbasedsegmentationandaugmentedbayesianfiltering AT ongleelingsharon multicellmigrationtrackingwithinangiogenicnetworksbydeeplearningbasedsegmentationandaugmentedbayesianfiltering AT dauwelsjustin multicellmigrationtrackingwithinangiogenicnetworksbydeeplearningbasedsegmentationandaugmentedbayesianfiltering AT asadaharuhiko multicellmigrationtrackingwithinangiogenicnetworksbydeeplearningbasedsegmentationandaugmentedbayesianfiltering |