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
Transfer Learning with Deep Convolutional Neural Networks for Classifying Cellular Morphological Changes
Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Pharmacy, Department of Pharmaceutical Biosciences. (Spjuth group)ORCID iD: 0000-0002-5295-010X
Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Pharmacy, Department of Pharmaceutical Biosciences. (Spjuth group)ORCID iD: 0000-0003-4046-9017
Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Pharmacy, Department of Pharmaceutical Biosciences.ORCID iD: 0000-0002-8083-2864
2019 (English)In: SLAS discovery : advancing life sciences R & D, ISSN 2472-5552, Vol. 24, no 4, p. 466-475Article in journal (Refereed) Published
Abstract [en]

The quantification and identification of cellular phenotypes from high-content microscopy images has proven to be very useful for understanding biological activity in response to different drug treatments. The traditional approach has been to use classical image analysis to quantify changes in cell morphology, which requires several nontrivial and independent analysis steps. Recently, convolutional neural networks have emerged as a compelling alternative, offering good predictive performance and the possibility to replace traditional workflows with a single network architecture. In this study, we applied the pretrained deep convolutional neural networks ResNet50, InceptionV3, and InceptionResnetV2 to predict cell mechanisms of action in response to chemical perturbations for two cell profiling datasets from the Broad Bioimage Benchmark Collection. These networks were pretrained on ImageNet, enabling much quicker model training. We obtain higher predictive accuracy than previously reported, between 95% and 97%. The ability to quickly and accurately distinguish between different cell morphologies from a scarce amount of labeled data illustrates the combined benefit of transfer learning and deep convolutional neural networks for interrogating cell-based images.

Place, publisher, year, edition, pages
2019. Vol. 24, no 4, p. 466-475
Keywords [en]
cell phenotypes, deep learning, high-content imaging, machine learning, transfer learning
National Category
Bioinformatics and Systems Biology
Identifiers
URN: urn:nbn:se:uu:diva-375566DOI: 10.1177/2472555218818756ISI: 000461840200004PubMedID: 30641024OAI: oai:DiVA.org:uu-375566DiVA, id: diva2:1284197
Funder
Swedish Foundation for Strategic Research Swedish National Infrastructure for Computing (SNIC)Available from: 2019-01-31 Created: 2019-01-31 Last updated: 2019-05-06Bibliographically approved

Open Access in DiVA

fulltext(938 kB)69 downloads
File information
File name FULLTEXT01.pdfFile size 938 kBChecksum SHA-512
544e9004b0f2a404958daa5fa80badb57eaf1afce2e17ade371b71432e901ef65c397ec421edf3a255399484f8c97ca4773a5b582fb13417911de9113e3fdc20
Type fulltextMimetype application/pdf

Other links

Publisher's full textPubMed

Search in DiVA

By author/editor
Kensert, AlexanderHarrison, Philip JSpjuth, Ola
By organisation
Department of Pharmaceutical Biosciences
Bioinformatics and Systems Biology

Search outside of DiVA

GoogleGoogle Scholar
Total: 69 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 121 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