Deep Learning for the Automated Feature Labelling of 3-Dimensional Imaged Placenta
Deep Learning for the Automated Feature Labelling of 3-Dimensional Imaged Placenta
3-D visualisation of cellular structures within the placenta is important for advancing research into the factors determining fetal growth, which are linked to chronic disease risk and quality of lifelong health. 2-D analysis can be challenging, and spatial interaction between structures can be easily missed, but obtaining 3-D structural images is extremely labour-intensive due to the high level of rigorous manual processing required. Deep neural networks are used to automate this previously manual process to construct fast and accurate 3-D structural images, which can be used for 3-D image analysis. The deep networks described in this chapter are trained to label both single cell, a fibroblast and a pericyte, and multicellular, endothelial, structures from within serial block-face scanning electron microscopy placental imaging. Automated labels are equivalent, pixel-to-pixel, to manual labels by over 98% on average over all cell structures and network architectures, and are able to successfully label unseen regions and stacks.
3-D image processing, Deep learning, Placenta
93
MacKay, Benita Scout
318d298f-5b38-43d7-b30d-8cd07f69acd4
Grant-Jacob, James
c5d144d8-3c43-4195-8e80-edd96bfda91b
Eason, R.W.
e38684c3-d18c-41b9-a4aa-def67283b020
Lewis, Rohan
caaeb97d-ea69-4f7b-8adb-5fa25e2d3502
Mills, Benjamin
05f1886e-96ef-420f-b856-4115f4ab36d0
30 April 2021
MacKay, Benita Scout
318d298f-5b38-43d7-b30d-8cd07f69acd4
Grant-Jacob, James
c5d144d8-3c43-4195-8e80-edd96bfda91b
Eason, R.W.
e38684c3-d18c-41b9-a4aa-def67283b020
Lewis, Rohan
caaeb97d-ea69-4f7b-8adb-5fa25e2d3502
Mills, Benjamin
05f1886e-96ef-420f-b856-4115f4ab36d0
MacKay, Benita Scout, Grant-Jacob, James, Eason, R.W., Lewis, Rohan and Mills, Benjamin
(2021)
Deep Learning for the Automated Feature Labelling of 3-Dimensional Imaged Placenta.
In,
Biomedical Engineering Systems and Technologies: 13th International Joint Conference, BIOSTEC 2020, Valletta, Malta, February 24–26, 2020, Revised Selected Papers.
1 ed.
Springer, .
(doi:10.1007/978-3-030-72379-8_6).
Record type:
Book Section
Abstract
3-D visualisation of cellular structures within the placenta is important for advancing research into the factors determining fetal growth, which are linked to chronic disease risk and quality of lifelong health. 2-D analysis can be challenging, and spatial interaction between structures can be easily missed, but obtaining 3-D structural images is extremely labour-intensive due to the high level of rigorous manual processing required. Deep neural networks are used to automate this previously manual process to construct fast and accurate 3-D structural images, which can be used for 3-D image analysis. The deep networks described in this chapter are trained to label both single cell, a fibroblast and a pericyte, and multicellular, endothelial, structures from within serial block-face scanning electron microscopy placental imaging. Automated labels are equivalent, pixel-to-pixel, to manual labels by over 98% on average over all cell structures and network architectures, and are able to successfully label unseen regions and stacks.
Text
placenta draft v8
- Author's Original
Restricted to Repository staff only
Request a copy
More information
e-pub ahead of print date: 30 March 2021
Published date: 30 April 2021
Keywords:
3-D image processing, Deep learning, Placenta
Identifiers
Local EPrints ID: 448184
URI: http://eprints.soton.ac.uk/id/eprint/448184
PURE UUID: 8ce0ba0d-71d3-4937-aa14-14040d33c63e
Catalogue record
Date deposited: 14 Apr 2021 16:40
Last modified: 28 Apr 2022 02:25
Export record
Altmetrics
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
