Show simple item record

dc.contributor.author
Chaitanya, Krishna
dc.contributor.author
Erdil, Ertunc
dc.contributor.author
Karani, Neerav
dc.contributor.author
Konukoglu, Ender
dc.contributor.editor
Larochelle, Hugo
dc.contributor.editor
Ranzato, Marc'Aurelio
dc.contributor.editor
Hadsell, Raia
dc.contributor.editor
Balcan, Maria F.
dc.contributor.editor
Lin, H.
dc.date.accessioned
2021-07-21T08:50:01Z
dc.date.available
2021-01-29T10:04:08Z
dc.date.available
2021-01-29T10:20:21Z
dc.date.available
2021-03-22T14:40:40Z
dc.date.available
2021-07-21T08:50:01Z
dc.date.issued
2021
dc.identifier.isbn
978-1-7138-2954-6
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/466629
dc.description.abstract
A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to pre-train a neural network with unlabeled data, followed by fine-tuning for a downstream task with limited annotations. Contrastive learning, a particular variant of SSL, is a powerful technique for learning image-level representations. In this work, we propose strategies for extending the contrastive learning framework for segmentation of volumetric medical images in the semi-supervised setting with limited annotations, by leveraging domain-specific and problem-specific cues. Specifically, we propose (1) novel contrasting strategies that leverage structural similarity across volumetric medical images (domain-specific cue) and (2) a local version of the contrastive loss to learn distinctive representations of local regions that are useful for per-pixel segmentation (problem-specific cue). We carry out an extensive evaluation on three Magnetic Resonance Imaging (MRI) datasets. In the limited annotation setting, the proposed method yields substantial improvements compared to other self-supervision and semi-supervised learning techniques. When combined with a simple data augmentation technique, the proposed method reaches within 8\% of benchmark performance using only two labeled MRI volumes for training. The code is made public at https://github.com/krishnabits001/domain_specific_cl.
en_US
dc.language.iso
en
en_US
dc.publisher
Curran 
en_US
dc.title
Contrastive learning of global and local features for medical image segmentation with limited annotations
en_US
dc.type
Conference Paper
dc.date.published
2020
ethz.book.title
Advances in Neural Information Processing Systems 33
en_US
ethz.pages.start
12546
en_US
ethz.pages.end
12558
en_US
ethz.event
34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020)
en_US
ethz.event.location
Online
en_US
ethz.event.date
December 6-12, 2020
en_US
ethz.notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.
en_US
ethz.publication.place
Red Hook, NY
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::09579 - Konukoglu, Ender / Konukoglu, Ender
en_US
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::09579 - Konukoglu, Ender / Konukoglu, Ender
en_US
ethz.identifier.url
https://papers.nips.cc/paper/2020/hash/949686ecef4ee20a62d16b4a2d7ccca3-Abstract.html
ethz.relation.hasPart
10.3929/ethz-b-000443425
ethz.date.deposited
2021-01-29T10:04:19Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-03-22T14:41:02Z
ethz.rosetta.lastUpdated
2022-03-29T10:34:01Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Contrastive%20learning%20of%20global%20and%20local%20features%20for%20medical%20image%20segmentation%20with%20limited%20annotations&rft.date=2021&rft.spage=12546&rft.epage=12558&rft.au=Chaitanya,%20Krishna&Erdil,%20Ertunc&Karani,%20Neerav&Konukoglu,%20Ender&rft.isbn=978-1-7138-2954-6&rft.genre=proceeding&rft.btitle=Advances%20in%20Neural%20Information%20Processing%20Systems%2033
 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