Deep learning for automatic segmentation of the nuclear envelope in electron microscopy data, trained with volunteer segmentations
Advancements in volume electron microscopy mean it is now possible to generate thousands of serial images at nanometre resolution overnight, yet the gold standard approach for data analysis remains manual segmentation by an expert microscopist, resulting in a critical research bottleneck. Although s...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal article |
| Language: | English |
| Published: |
Wiley
2021
|
| _version_ | 1826292209008246784 |
|---|---|
| author | Spiers, H Songhurst, H Nightingale, L de Folter, J Hutchings, R Peddie, CJ Weston, A Strange, A Hindmarsh, S Lintott, CJ Collinson, LM Jones, ML |
| author2 | Zooniverse Volunteer Community |
| author_facet | Zooniverse Volunteer Community Spiers, H Songhurst, H Nightingale, L de Folter, J Hutchings, R Peddie, CJ Weston, A Strange, A Hindmarsh, S Lintott, CJ Collinson, LM Jones, ML |
| author_sort | Spiers, H |
| collection | OXFORD |
| description | Advancements in volume electron microscopy mean it is now possible to generate thousands of serial images at nanometre resolution overnight, yet the gold standard approach for data analysis remains manual segmentation by an expert microscopist, resulting in a critical research bottleneck. Although some machine learning approaches exist in this domain, we remain far from realizing the aspiration of a highly accurate, yet generic, automated analysis approach, with a major obstacle being lack of sufficient high-quality ground-truth data. To address this, we developed a novel citizen science project, Etch a Cell, to enable volunteers to manually segment the nuclear envelope (NE) of HeLa cells imaged with serial blockface scanning electron microscopy. We present our approach for aggregating multiple volunteer annotations to generate a high-quality consensus segmentation and demonstrate that data produced exclusively by volunteers can be used to train a highly accurate machine learning algorithm for automatic segmentation of the NE, which we share here, in addition to our archived benchmark data. |
| first_indexed | 2024-03-07T03:11:09Z |
| format | Journal article |
| id | oxford-uuid:b43d8a76-b7fa-4646-9756-9f0ebc30ea05 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T03:11:09Z |
| publishDate | 2021 |
| publisher | Wiley |
| record_format | dspace |
| spelling | oxford-uuid:b43d8a76-b7fa-4646-9756-9f0ebc30ea052022-03-27T04:24:51ZDeep learning for automatic segmentation of the nuclear envelope in electron microscopy data, trained with volunteer segmentationsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:b43d8a76-b7fa-4646-9756-9f0ebc30ea05EnglishSymplectic ElementsWiley2021Spiers, HSonghurst, HNightingale, Lde Folter, JHutchings, RPeddie, CJWeston, AStrange, AHindmarsh, SLintott, CJCollinson, LMJones, MLZooniverse Volunteer CommunityAdvancements in volume electron microscopy mean it is now possible to generate thousands of serial images at nanometre resolution overnight, yet the gold standard approach for data analysis remains manual segmentation by an expert microscopist, resulting in a critical research bottleneck. Although some machine learning approaches exist in this domain, we remain far from realizing the aspiration of a highly accurate, yet generic, automated analysis approach, with a major obstacle being lack of sufficient high-quality ground-truth data. To address this, we developed a novel citizen science project, Etch a Cell, to enable volunteers to manually segment the nuclear envelope (NE) of HeLa cells imaged with serial blockface scanning electron microscopy. We present our approach for aggregating multiple volunteer annotations to generate a high-quality consensus segmentation and demonstrate that data produced exclusively by volunteers can be used to train a highly accurate machine learning algorithm for automatic segmentation of the NE, which we share here, in addition to our archived benchmark data. |
| spellingShingle | Spiers, H Songhurst, H Nightingale, L de Folter, J Hutchings, R Peddie, CJ Weston, A Strange, A Hindmarsh, S Lintott, CJ Collinson, LM Jones, ML Deep learning for automatic segmentation of the nuclear envelope in electron microscopy data, trained with volunteer segmentations |
| title | Deep learning for automatic segmentation of the nuclear envelope in electron microscopy data, trained with volunteer segmentations |
| title_full | Deep learning for automatic segmentation of the nuclear envelope in electron microscopy data, trained with volunteer segmentations |
| title_fullStr | Deep learning for automatic segmentation of the nuclear envelope in electron microscopy data, trained with volunteer segmentations |
| title_full_unstemmed | Deep learning for automatic segmentation of the nuclear envelope in electron microscopy data, trained with volunteer segmentations |
| title_short | Deep learning for automatic segmentation of the nuclear envelope in electron microscopy data, trained with volunteer segmentations |
| title_sort | deep learning for automatic segmentation of the nuclear envelope in electron microscopy data trained with volunteer segmentations |
| work_keys_str_mv | AT spiersh deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT songhursth deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT nightingalel deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT defolterj deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT hutchingsr deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT peddiecj deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT westona deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT strangea deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT hindmarshs deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT lintottcj deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT collinsonlm deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations AT jonesml deeplearningforautomaticsegmentationofthenuclearenvelopeinelectronmicroscopydatatrainedwithvolunteersegmentations |