Cargando…

Tracking cell lineages in 3D by incremental deep learning

Deep learning is emerging as a powerful approach for bioimage analysis. Its use in cell tracking is limited by the scarcity of annotated data for the training of deep-learning models. Moreover, annotation, training, prediction, and proofreading currently lack a unified user interface. We present ELE...

Descripción completa

Detalles Bibliográficos
Autores principales: Sugawara, Ko, Çevrim, Çağrı, Averof, Michalis
Formato: Online Artículo Texto
Lenguaje:English
Publicado: eLife Sciences Publications, Ltd 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8741210/
https://www.ncbi.nlm.nih.gov/pubmed/34989675
http://dx.doi.org/10.7554/eLife.69380
_version_ 1784629433761529856
author Sugawara, Ko
Çevrim, Çağrı
Averof, Michalis
author_facet Sugawara, Ko
Çevrim, Çağrı
Averof, Michalis
author_sort Sugawara, Ko
collection PubMed
description Deep learning is emerging as a powerful approach for bioimage analysis. Its use in cell tracking is limited by the scarcity of annotated data for the training of deep-learning models. Moreover, annotation, training, prediction, and proofreading currently lack a unified user interface. We present ELEPHANT, an interactive platform for 3D cell tracking that addresses these challenges by taking an incremental approach to deep learning. ELEPHANT provides an interface that seamlessly integrates cell track annotation, deep learning, prediction, and proofreading. This enables users to implement cycles of incremental learning starting from a few annotated nuclei. Successive prediction-validation cycles enrich the training data, leading to rapid improvements in tracking performance. We test the software’s performance against state-of-the-art methods and track lineages spanning the entire course of leg regeneration in a crustacean over 1 week (504 timepoints). ELEPHANT yields accurate, fully-validated cell lineages with a modest investment in time and effort.
format Online
Article
Text
id pubmed-8741210
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher eLife Sciences Publications, Ltd
record_format MEDLINE/PubMed
spelling pubmed-87412102022-01-11 Tracking cell lineages in 3D by incremental deep learning Sugawara, Ko Çevrim, Çağrı Averof, Michalis eLife Developmental Biology Deep learning is emerging as a powerful approach for bioimage analysis. Its use in cell tracking is limited by the scarcity of annotated data for the training of deep-learning models. Moreover, annotation, training, prediction, and proofreading currently lack a unified user interface. We present ELEPHANT, an interactive platform for 3D cell tracking that addresses these challenges by taking an incremental approach to deep learning. ELEPHANT provides an interface that seamlessly integrates cell track annotation, deep learning, prediction, and proofreading. This enables users to implement cycles of incremental learning starting from a few annotated nuclei. Successive prediction-validation cycles enrich the training data, leading to rapid improvements in tracking performance. We test the software’s performance against state-of-the-art methods and track lineages spanning the entire course of leg regeneration in a crustacean over 1 week (504 timepoints). ELEPHANT yields accurate, fully-validated cell lineages with a modest investment in time and effort. eLife Sciences Publications, Ltd 2022-01-06 /pmc/articles/PMC8741210/ /pubmed/34989675 http://dx.doi.org/10.7554/eLife.69380 Text en © 2022, Sugawara et al https://creativecommons.org/licenses/by/4.0/This article is distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use and redistribution provided that the original author and source are credited.
spellingShingle Developmental Biology
Sugawara, Ko
Çevrim, Çağrı
Averof, Michalis
Tracking cell lineages in 3D by incremental deep learning
title Tracking cell lineages in 3D by incremental deep learning
title_full Tracking cell lineages in 3D by incremental deep learning
title_fullStr Tracking cell lineages in 3D by incremental deep learning
title_full_unstemmed Tracking cell lineages in 3D by incremental deep learning
title_short Tracking cell lineages in 3D by incremental deep learning
title_sort tracking cell lineages in 3d by incremental deep learning
topic Developmental Biology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8741210/
https://www.ncbi.nlm.nih.gov/pubmed/34989675
http://dx.doi.org/10.7554/eLife.69380
work_keys_str_mv AT sugawarako trackingcelllineagesin3dbyincrementaldeeplearning
AT cevrimcagrı trackingcelllineagesin3dbyincrementaldeeplearning
AT averofmichalis trackingcelllineagesin3dbyincrementaldeeplearning