Show simple item record

dc.contributor.author
Gomariz, Alvaro
dc.contributor.author
Egli, Raphael
dc.contributor.author
Portenier, Tiziano
dc.contributor.author
Nombela-Arrieta, César
dc.contributor.author
Goksel, Orcun
dc.date.accessioned
2021-06-17T06:32:19Z
dc.date.available
2021-06-11T02:25:00Z
dc.date.available
2021-06-17T06:32:19Z
dc.date.issued
2021
dc.identifier.isbn
978-1-6654-1246-9
en_US
dc.identifier.isbn
978-1-6654-1245-2
en_US
dc.identifier.isbn
978-1-6654-2947-4
en_US
dc.identifier.other
10.1109/ISBI48211.2021.9434158
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/489158
dc.description.abstract
Fluorescence microscopy images contain several channels, each indicating a marker staining the sample. Since many different marker combinations are utilized in practice, it has been challenging to apply deep learning based segmentation models, which expect a predefined channel combination for all training samples as well as at inference for future application. Recent work circumvents this problem using a modality attention approach to be effective across any possible marker combination. However, for combinations that do not exist in a labeled training dataset, one cannot have any estimation of potential segmentation quality if that combination is encountered during inference. Without this, not only one lacks quality assurance but one also does not know where to put any additional imaging and labeling effort. We herein propose a method to estimate segmentation quality on unlabeled images by (i) estimating both aleatoric and epistemic uncertainties of convolutional neural networks for image segmentation, and (ii) training a Random Forest model for the interpretation of uncertainty features via regression to their corresponding segmentation metrics. Additionally, we demonstrate that including these uncertainty measures during training can provide an improvement on segmentation performance.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.title
Utilizing Uncertainty Estimation in Deep Learning Segmentation of Fluorescence Microscopy Images with Missing Markers
en_US
dc.type
Conference Paper
dc.date.published
2021-05-25
ethz.book.title
2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)
en_US
ethz.pages.start
371
en_US
ethz.pages.end
374
en_US
ethz.event
18th International Symposium on Biomedical Imaging (ISBI 2021)
en_US
ethz.event.location
Nice, France
en_US
ethz.event.date
April 13-16, 2021
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Piscataway, NJ
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::09528 - Göksel, Orçun (ehemalig) / Göksel, Orçun (former)
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::09528 - Göksel, Orçun (ehemalig) / Göksel, Orçun (former)
ethz.date.deposited
2021-06-11T02:25:09Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-06-17T06:32:26Z
ethz.rosetta.lastUpdated
2022-03-29T08:49:50Z
ethz.rosetta.exportRequired
true
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Utilizing%20Uncertainty%20Estimation%20in%20Deep%20Learning%20Segmentation%20of%20Fluorescence%20Microscopy%20Images%20with%20Missing%20Markers&rft.date=2021&rft.spage=371&rft.epage=374&rft.au=Gomariz,%20Alvaro&Egli,%20Raphael&Portenier,%20Tiziano&Nombela-Arrieta,%20C%C3%A9sar&Goksel,%20Orcun&rft.isbn=978-1-6654-1246-9&978-1-6654-1245-2&978-1-6654-2947-4&rft.genre=proceeding&rft_id=info:doi/10.1109/ISBI48211.2021.9434158&rft.btitle=2021%20IEEE%2018th%20International%20Symposium%20on%20Biomedical%20Imaging%20(ISBI)
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record