Show simple item record

dc.contributor.author
Kuo, Willy
dc.contributor.author
Rossinelli, Diego
dc.contributor.author
Schulz, Georg
dc.contributor.author
Wenger, Roland H.
dc.contributor.author
Hieber, Simone
dc.contributor.author
Müller, Bert
dc.contributor.author
Kurtcuoglu, Vartan
dc.date.accessioned
2023-11-08T15:16:48Z
dc.date.available
2023-09-18T09:45:44Z
dc.date.available
2023-09-18T09:46:52Z
dc.date.available
2023-11-08T15:16:48Z
dc.date.issued
2023-08
dc.identifier.issn
2052-4463
dc.identifier.other
10.1038/s41597-023-02407-5
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/632024
dc.identifier.doi
10.3929/ethz-b-000632024
dc.description.abstract
The performance of machine learning algorithms, when used for segmenting 3D biomedical images, does not reach the level expected based on results achieved with 2D photos. This may be explained by the comparative lack of high-volume, high-quality training datasets, which require state-of-the-art imaging facilities, domain experts for annotation and large computational and personal resources. The HR-Kidney dataset presented in this work bridges this gap by providing 1.7 TB of artefact-corrected synchrotron radiation-based X-ray phase-contrast microtomography images of whole mouse kidneys and validated segmentations of 33 729 glomeruli, which corresponds to a one to two orders of magnitude increase over currently available biomedical datasets. The image sets also contain the underlying raw data, threshold- and morphology-based semi-automatic segmentations of renal vasculature and uriniferous tubules, as well as true 3D manual annotations. We therewith provide a broad basis for the scientific community to build upon and expand in the fields of image processing, data augmentation and machine learning, in particular unsupervised and semi-supervised learning investigations, as well as transfer learning and generative adversarial networks.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Nature
en_US
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.title
Terabyte-scale supervised 3D training and benchmarking dataset of the mouse kidney
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 4.0 International
dc.date.published
2023-08-03
ethz.journal.title
Scientific Data
ethz.journal.volume
10
en_US
ethz.journal.issue
1
en_US
ethz.journal.abbreviated
Sci Data
ethz.pages.start
510
en_US
ethz.size
10 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.
en_US
ethz.relation.isSupplementedBy
handle/20.500.11850/497183
ethz.date.deposited
2023-09-18T09:45:44Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2023-11-08T15:16:53Z
ethz.rosetta.lastUpdated
2024-02-03T06:05:34Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Terabyte-scale%20supervised%203D%20training%20and%20benchmarking%20dataset%20of%20the%20mouse%20kidney&rft.jtitle=Scientific%20Data&rft.date=2023-08&rft.volume=10&rft.issue=1&rft.spage=510&rft.issn=2052-4463&rft.au=Kuo,%20Willy&Rossinelli,%20Diego&Schulz,%20Georg&Wenger,%20Roland%20H.&Hieber,%20Simone&rft.genre=article&rft_id=info:doi/10.1038/s41597-023-02407-5&
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record