liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Refacing: Reconstructing Anonymized Facial Features Using GANS
Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
2019 (English)Conference paper (Refereed)
Abstract [en]

Anonymization of medical images is necessary for protecting the identity of the test subjects, and is therefore an essential step in data sharing. However, recent developments in deep learning may raise the bar on the amount of distortion that needs to be applied to guarantee anonymity. To test such possibilities, we have applied the novel CycleGAN unsupervised image-to-image translation framework on sagittal slices of T1 MR images, in order to reconstruct facial features from anonymized data. We applied the CycleGAN framework on both face-blurred and face-removed images. Our results show that face blurring may not provide adequate protection against malicious attempts at identifying the subjects, while face removal provides more robust anonymization, but is still partially reversible.

Place, publisher, year, edition, pages
2019.
Keywords [en]
Face, Image reconstruction, Training, Hospitals, Biomedical imaging, Facial features, Gallium nitride, MRI, anonymization, GANs, image-to-image translation
National Category
Medical Engineering
Identifiers
URN: urn:nbn:se:liu:diva-159516DOI: 10.1109/ISBI.2019.8759515OAI: oai:DiVA.org:liu-159516DiVA, id: diva2:1341793
Conference
2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)
Available from: 2019-08-12 Created: 2019-08-12 Last updated: 2019-08-12

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Authority records BETA

Abramian, DavidEklund, Anders

Search in DiVA

By author/editor
Abramian, DavidEklund, Anders
By organisation
Division of Biomedical EngineeringFaculty of Science & EngineeringThe Division of Statistics and Machine LearningCenter for Medical Image Science and Visualization (CMIV)
Medical Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 78 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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