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
Segmentation of bones in medical dual-energy computed tomography volumes using the 3D U-Net
Linköping University, Department of Medical and Health Sciences. Linköping University, Faculty of Medicine and Health Sciences. Region Östergötland, Center for Surgery, Orthopaedics and Cancer Treatment, Department of Radiation Physics.
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV). Region Östergötland, Center for Surgery, Orthopaedics and Cancer Treatment, Department of Radiation Physics.ORCID iD: 0000-0002-9072-2204
Linköping University, Department of Medical and Health Sciences, Division of Radiological Sciences. Region Östergötland, Center for Diagnostics, Medical radiation physics. Linköping University, Center for Medical Image Science and Visualization (CMIV). Linköping University, Faculty of Medicine and Health Sciences.ORCID iD: 0000-0003-3352-8330
Linköping University, Department of Medical and Health Sciences, Division of Radiological Sciences. Linköping University, Faculty of Medicine and Health Sciences. Region Östergötland, Center for Surgery, Orthopaedics and Cancer Treatment, Department of Radiation Physics. Linköping University, Center for Medical Image Science and Visualization (CMIV). Karolinska Univ Hosp, Sweden.
Show others and affiliations
2020 (English)In: Physica medica (Testo stampato), ISSN 1120-1797, E-ISSN 1724-191X, Vol. 69, p. 241-247Article in journal (Refereed) Published
Abstract [en]

Deep learning algorithms have improved the speed and quality of segmentation for certain tasks in medical imaging. The aim of this work is to design and evaluate an algorithm capable of segmenting bones in dual-energy CT data sets. A convolutional neural network based on the 3D U-Net architecture was implemented and evaluated using high tube voltage images, mixed images and dual-energy images from 30 patients. The network performed well on all the data sets; the mean Dice coefficient for the test data was larger than 0.963. Of special interest is that it performed better on dual-energy CT volumes compared to mixed images that mimicked images taken at 120 kV. The corresponding increase in the Dice coefficient from 0.965 to 0.966 was small since the enhancements were mainly at the edges of the bones. The method can easily be extended to the segmentation of multi-energy CT data.

Place, publisher, year, edition, pages
Elsevier, 2020. Vol. 69, p. 241-247
Keywords [en]
Deep learning; Convolutional neural network; Segmentation; Dual-energy computed tomography
National Category
Radiology, Nuclear Medicine and Medical Imaging
Identifiers
URN: urn:nbn:se:liu:diva-163373DOI: 10.1016/j.ejmp.2019.12.014ISI: 000506632700030PubMedID: 31918376Scopus ID: 2-s2.0-85077447470OAI: oai:DiVA.org:liu-163373DiVA, id: diva2:1391067
Note

Funding Agencies| [SNIC 2018/7-22]; [LiO-724181]; [CAN 2017/1029]; [VRNT 2016-05033]

Available from: 2020-02-03 Created: 2020-02-03 Last updated: 2020-02-18Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Search in DiVA

By author/editor
Sanchez, Jose Carlos GonzalezMagnusson, MariaSandborg, MichaelCarlsson Tedgren, ÅsaMalusek, Alexandr
By organisation
Department of Medical and Health SciencesFaculty of Medicine and Health SciencesDepartment of Radiation PhysicsComputer VisionFaculty of Science & EngineeringCenter for Medical Image Science and Visualization (CMIV)Division of Radiological SciencesMedical radiation physics
In the same journal
Physica medica (Testo stampato)
Radiology, Nuclear Medicine and Medical Imaging

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 2 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