3DeeCellTracker, a deep learning-based pipeline for segmenting and tracking cells in 3D time lapse images
Despite recent improvements in microscope technologies, segmenting and tracking cells in three-dimensional time-lapse images (3D + T images) to extract their dynamic positions and activities remains a considerable bottleneck in the field. We developed a deep learning-based software pipeline, 3DeeCel...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
eLife Sciences Publications Ltd
2021-03-01
|
| Series: | eLife |
| Subjects: | |
| Online Access: | https://elifesciences.org/articles/59187 |
| _version_ | 1797991974843711488 |
|---|---|
| author | Chentao Wen Takuya Miura Venkatakaushik Voleti Kazushi Yamaguchi Motosuke Tsutsumi Kei Yamamoto Kohei Otomo Yukako Fujie Takayuki Teramoto Takeshi Ishihara Kazuhiro Aoki Tomomi Nemoto Elizabeth MC Hillman Koutarou D Kimura |
| author_facet | Chentao Wen Takuya Miura Venkatakaushik Voleti Kazushi Yamaguchi Motosuke Tsutsumi Kei Yamamoto Kohei Otomo Yukako Fujie Takayuki Teramoto Takeshi Ishihara Kazuhiro Aoki Tomomi Nemoto Elizabeth MC Hillman Koutarou D Kimura |
| author_sort | Chentao Wen |
| collection | DOAJ |
| description | Despite recent improvements in microscope technologies, segmenting and tracking cells in three-dimensional time-lapse images (3D + T images) to extract their dynamic positions and activities remains a considerable bottleneck in the field. We developed a deep learning-based software pipeline, 3DeeCellTracker, by integrating multiple existing and new techniques including deep learning for tracking. With only one volume of training data, one initial correction, and a few parameter changes, 3DeeCellTracker successfully segmented and tracked ~100 cells in both semi-immobilized and ‘straightened’ freely moving worm's brain, in a naturally beating zebrafish heart, and ~1000 cells in a 3D cultured tumor spheroid. While these datasets were imaged with highly divergent optical systems, our method tracked 90–100% of the cells in most cases, which is comparable or superior to previous results. These results suggest that 3DeeCellTracker could pave the way for revealing dynamic cell activities in image datasets that have been difficult to analyze. |
| first_indexed | 2024-04-11T09:00:34Z |
| format | Article |
| id | doaj.art-798a037c858b49c6b741110877257a1d |
| institution | Directory Open Access Journal |
| issn | 2050-084X |
| language | English |
| last_indexed | 2024-04-11T09:00:34Z |
| publishDate | 2021-03-01 |
| publisher | eLife Sciences Publications Ltd |
| record_format | Article |
| series | eLife |
| spelling | doaj.art-798a037c858b49c6b741110877257a1d2022-12-22T04:32:47ZengeLife Sciences Publications LtdeLife2050-084X2021-03-011010.7554/eLife.591873DeeCellTracker, a deep learning-based pipeline for segmenting and tracking cells in 3D time lapse imagesChentao Wen0https://orcid.org/0000-0002-8609-476XTakuya Miura1Venkatakaushik Voleti2Kazushi Yamaguchi3Motosuke Tsutsumi4https://orcid.org/0000-0002-5832-3828Kei Yamamoto5https://orcid.org/0000-0003-2712-1550Kohei Otomo6https://orcid.org/0000-0002-5322-6295Yukako Fujie7Takayuki Teramoto8https://orcid.org/0000-0001-7060-7148Takeshi Ishihara9https://orcid.org/0000-0001-9175-3072Kazuhiro Aoki10https://orcid.org/0000-0001-7263-1555Tomomi Nemoto11https://orcid.org/0000-0001-6102-1495Elizabeth MC Hillman12https://orcid.org/0000-0001-5511-1451Koutarou D Kimura13https://orcid.org/0000-0002-3359-1578Graduate School of Science, Nagoya City University, Nagoya, JapanDepartment of Biological Sciences, Graduate School of Science, Osaka University, Toyonaka, JapanDepartments of Biomedical Engineering and Radiology and the Zuckerman Mind Brain Behavior Institute, Columbia University, New York, United StatesGraduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan; National Institute for Physiological Sciences, Okazaki, JapanNational Institute for Physiological Sciences, Okazaki, Japan; Exploratory Research Center on Life and Living Systems, Okazaki, JapanNational Institute for Basic Biology, National Institutes of Natural Sciences, Okazaki, Japan; The Graduate School for Advanced Study, Hayama, JapanNational Institute for Physiological Sciences, Okazaki, Japan; Exploratory Research Center on Life and Living Systems, Okazaki, Japan; The Graduate School for Advanced Study, Hayama, JapanDepartment of Biological Sciences, Graduate School of Science, Osaka University, Toyonaka, JapanDepartment of Biology, Faculty of Science, Kyushu University, Fukuoka, JapanDepartment of Biology, Faculty of Science, Kyushu University, Fukuoka, JapanExploratory Research Center on Life and Living Systems, Okazaki, Japan; National Institute for Basic Biology, National Institutes of Natural Sciences, Okazaki, Japan; The Graduate School for Advanced Study, Hayama, JapanNational Institute for Physiological Sciences, Okazaki, Japan; Exploratory Research Center on Life and Living Systems, Okazaki, Japan; The Graduate School for Advanced Study, Hayama, JapanDepartments of Biomedical Engineering and Radiology and the Zuckerman Mind Brain Behavior Institute, Columbia University, New York, United StatesGraduate School of Science, Nagoya City University, Nagoya, Japan; Department of Biological Sciences, Graduate School of Science, Osaka University, Toyonaka, Japan; RIKEN center for Advanced Intelligence Project, Tokyo, JapanDespite recent improvements in microscope technologies, segmenting and tracking cells in three-dimensional time-lapse images (3D + T images) to extract their dynamic positions and activities remains a considerable bottleneck in the field. We developed a deep learning-based software pipeline, 3DeeCellTracker, by integrating multiple existing and new techniques including deep learning for tracking. With only one volume of training data, one initial correction, and a few parameter changes, 3DeeCellTracker successfully segmented and tracked ~100 cells in both semi-immobilized and ‘straightened’ freely moving worm's brain, in a naturally beating zebrafish heart, and ~1000 cells in a 3D cultured tumor spheroid. While these datasets were imaged with highly divergent optical systems, our method tracked 90–100% of the cells in most cases, which is comparable or superior to previous results. These results suggest that 3DeeCellTracker could pave the way for revealing dynamic cell activities in image datasets that have been difficult to analyze.https://elifesciences.org/articles/59187cell trackingbioimagingdeep learningquantitative biology |
| spellingShingle | Chentao Wen Takuya Miura Venkatakaushik Voleti Kazushi Yamaguchi Motosuke Tsutsumi Kei Yamamoto Kohei Otomo Yukako Fujie Takayuki Teramoto Takeshi Ishihara Kazuhiro Aoki Tomomi Nemoto Elizabeth MC Hillman Koutarou D Kimura 3DeeCellTracker, a deep learning-based pipeline for segmenting and tracking cells in 3D time lapse images eLife cell tracking bioimaging deep learning quantitative biology |
| title | 3DeeCellTracker, a deep learning-based pipeline for segmenting and tracking cells in 3D time lapse images |
| title_full | 3DeeCellTracker, a deep learning-based pipeline for segmenting and tracking cells in 3D time lapse images |
| title_fullStr | 3DeeCellTracker, a deep learning-based pipeline for segmenting and tracking cells in 3D time lapse images |
| title_full_unstemmed | 3DeeCellTracker, a deep learning-based pipeline for segmenting and tracking cells in 3D time lapse images |
| title_short | 3DeeCellTracker, a deep learning-based pipeline for segmenting and tracking cells in 3D time lapse images |
| title_sort | 3deecelltracker a deep learning based pipeline for segmenting and tracking cells in 3d time lapse images |
| topic | cell tracking bioimaging deep learning quantitative biology |
| url | https://elifesciences.org/articles/59187 |
| work_keys_str_mv | AT chentaowen 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT takuyamiura 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT venkatakaushikvoleti 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT kazushiyamaguchi 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT motosuketsutsumi 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT keiyamamoto 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT koheiotomo 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT yukakofujie 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT takayukiteramoto 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT takeshiishihara 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT kazuhiroaoki 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT tomominemoto 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT elizabethmchillman 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages AT koutaroudkimura 3deecelltrackeradeeplearningbasedpipelineforsegmentingandtrackingcellsin3dtimelapseimages |