Machine learning enhanced cell tracking
Quantifying cell biology in space and time requires computational methods to detect cells, measure their properties, and assemble these into meaningful trajectories. In this aspect, machine learning (ML) is having a transformational effect on bioimage analysis, now enabling robust cell detection in...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Bioinformatics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbinf.2023.1228989/full |
| _version_ | 1797779994437484544 |
|---|---|
| author | Christopher J. Soelistyo Christopher J. Soelistyo Kristina Ulicna Kristina Ulicna Alan R. Lowe Alan R. Lowe Alan R. Lowe |
| author_facet | Christopher J. Soelistyo Christopher J. Soelistyo Kristina Ulicna Kristina Ulicna Alan R. Lowe Alan R. Lowe Alan R. Lowe |
| author_sort | Christopher J. Soelistyo |
| collection | DOAJ |
| description | Quantifying cell biology in space and time requires computational methods to detect cells, measure their properties, and assemble these into meaningful trajectories. In this aspect, machine learning (ML) is having a transformational effect on bioimage analysis, now enabling robust cell detection in multidimensional image data. However, the task of cell tracking, or constructing accurate multi-generational lineages from imaging data, remains an open challenge. Most cell tracking algorithms are largely based on our prior knowledge of cell behaviors, and as such, are difficult to generalize to new and unseen cell types or datasets. Here, we propose that ML provides the framework to learn aspects of cell behavior using cell tracking as the task to be learned. We suggest that advances in representation learning, cell tracking datasets, metrics, and methods for constructing and evaluating tracking solutions can all form part of an end-to-end ML-enhanced pipeline. These developments will lead the way to new computational methods that can be used to understand complex, time-evolving biological systems. |
| first_indexed | 2024-03-12T23:38:22Z |
| format | Article |
| id | doaj.art-08dfdafd074644e08e6b7331476491b8 |
| institution | Directory Open Access Journal |
| issn | 2673-7647 |
| language | English |
| last_indexed | 2024-03-12T23:38:22Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioinformatics |
| spelling | doaj.art-08dfdafd074644e08e6b7331476491b82023-07-15T03:25:06ZengFrontiers Media S.A.Frontiers in Bioinformatics2673-76472023-07-01310.3389/fbinf.2023.12289891228989Machine learning enhanced cell trackingChristopher J. Soelistyo0Christopher J. Soelistyo1Kristina Ulicna2Kristina Ulicna3Alan R. Lowe4Alan R. Lowe5Alan R. Lowe6Department of Structural and Molecular Biology, University College London, London, United KingdomInstitute for the Physics of Living Systems, London, United KingdomDepartment of Structural and Molecular Biology, University College London, London, United KingdomInstitute for the Physics of Living Systems, London, United KingdomDepartment of Structural and Molecular Biology, University College London, London, United KingdomInstitute for the Physics of Living Systems, London, United KingdomAlan Turing Institute, London, United KingdomQuantifying cell biology in space and time requires computational methods to detect cells, measure their properties, and assemble these into meaningful trajectories. In this aspect, machine learning (ML) is having a transformational effect on bioimage analysis, now enabling robust cell detection in multidimensional image data. However, the task of cell tracking, or constructing accurate multi-generational lineages from imaging data, remains an open challenge. Most cell tracking algorithms are largely based on our prior knowledge of cell behaviors, and as such, are difficult to generalize to new and unseen cell types or datasets. Here, we propose that ML provides the framework to learn aspects of cell behavior using cell tracking as the task to be learned. We suggest that advances in representation learning, cell tracking datasets, metrics, and methods for constructing and evaluating tracking solutions can all form part of an end-to-end ML-enhanced pipeline. These developments will lead the way to new computational methods that can be used to understand complex, time-evolving biological systems.https://www.frontiersin.org/articles/10.3389/fbinf.2023.1228989/fullmachine learning (ML)computer visiontrackingcell trackingbioimage analysisoptimisation |
| spellingShingle | Christopher J. Soelistyo Christopher J. Soelistyo Kristina Ulicna Kristina Ulicna Alan R. Lowe Alan R. Lowe Alan R. Lowe Machine learning enhanced cell tracking Frontiers in Bioinformatics machine learning (ML) computer vision tracking cell tracking bioimage analysis optimisation |
| title | Machine learning enhanced cell tracking |
| title_full | Machine learning enhanced cell tracking |
| title_fullStr | Machine learning enhanced cell tracking |
| title_full_unstemmed | Machine learning enhanced cell tracking |
| title_short | Machine learning enhanced cell tracking |
| title_sort | machine learning enhanced cell tracking |
| topic | machine learning (ML) computer vision tracking cell tracking bioimage analysis optimisation |
| url | https://www.frontiersin.org/articles/10.3389/fbinf.2023.1228989/full |
| work_keys_str_mv | AT christopherjsoelistyo machinelearningenhancedcelltracking AT christopherjsoelistyo machinelearningenhancedcelltracking AT kristinaulicna machinelearningenhancedcelltracking AT kristinaulicna machinelearningenhancedcelltracking AT alanrlowe machinelearningenhancedcelltracking AT alanrlowe machinelearningenhancedcelltracking AT alanrlowe machinelearningenhancedcelltracking |