Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Analysis of the Human Protein Atlas Image Classification competition
KTH, Centres, Science for Life Laboratory, SciLifeLab. KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH).ORCID iD: 0000-0002-0291-926X
KTH, Centres, Science for Life Laboratory, SciLifeLab. KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH).ORCID iD: 0000-0002-0028-5865
KTH, Centres, Science for Life Laboratory, SciLifeLab. KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH).ORCID iD: 0000-0001-7375-9681
KTH, Centres, Science for Life Laboratory, SciLifeLab. KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH).ORCID iD: 0000-0002-2387-3491
Show others and affiliations
2019 (English)In: Nature Methods, ISSN 1548-7091, E-ISSN 1548-7105, Vol. 16, no 12, p. 1254-+Article in journal (Refereed) Published
Abstract [en]

Pinpointing subcellular protein localizations from microscopy images is easy to the trained eye, but challenging to automate. Based on the Human Protein Atlas image collection, we held a competition to identify deep learning solutions to solve this task. Challenges included training on highly imbalanced classes and predicting multiple labels per image. Over 3 months, 2,172 teams participated. Despite convergence on popular networks and training techniques, there was considerable variety among the solutions. Participants applied strategies for modifying neural networks and loss functions, augmenting data and using pretrained networks. The winning models far outperformed our previous effort at multi-label classification of protein localization patterns by similar to 20%. These models can be used as classifiers to annotate new images, feature extractors to measure pattern similarity or pretrained networks for a wide range of biological applications.

Place, publisher, year, edition, pages
NATURE PUBLISHING GROUP , 2019. Vol. 16, no 12, p. 1254-+
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-266288DOI: 10.1038/s41592-019-0658-6ISI: 000499653100025PubMedID: 31780840Scopus ID: 2-s2.0-85075762199OAI: oai:DiVA.org:kth-266288DiVA, id: diva2:1383083
Note

Correction in DOI: 10.1038/s41592-019-0699-x ISI: 000508582900046QC 20200329

Available from: 2020-01-07 Created: 2020-01-07 Last updated: 2020-03-29Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records BETA

Ouyang, WeiWinsnes, Casper F.Hjelmare, MartinÅkesson, LovisaXu, HaoSullivan, D. P.

Search in DiVA

By author/editor
Ouyang, WeiWinsnes, Casper F.Hjelmare, MartinÅkesson, LovisaXu, HaoSullivan, D. P.
By organisation
Science for Life Laboratory, SciLifeLabSchool of Engineering Sciences in Chemistry, Biotechnology and Health (CBH)
In the same journal
Nature Methods
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 4 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf