umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Hildeman, A., Bolin, D., Wallin, J., Johansson, A., Nyholm, T., Asklund, T., and Yu, J. Whole-brain substitute CT generation using Markov random field mixture models.
Department of Mathematical Sciences, Chalmers University of Technology, Sweden.
Department of Mathematical Sciences, Chalmers University of Technology, Sweden.
Department of Statistics, Lund University.
Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
Visa övriga samt affilieringar
2016 (Engelska)Manuskript (preprint) (Övrigt vetenskapligt)
Abstract [en]

Computed tomography (CT) equivalent information is needed for attenuation correction in PET imaging and for dose planning in radiotherapy. Prior work has shown that Gaussian mixture models can be used to generate a substitute CT (s-CT) image from a specific set of MRI modalities. This work introduces a more flexible class of mixture models for s-CT generation, that incorporates spatial dependency in the data through a Markov random field prior on the latent field of class memberships associated with a mixture model. Furthermore, the mixture distributions are extended from Gaussian to normal inverse Gaussian (NIG), allowing heavier tails and skewness. The amount of data needed to train a model for s-CT generation is of the order of 10^8 voxels. The computational efficiency of the parameter estimationand prediction methods are hence paramount, especially when spatial dependency is included in the models. A stochastic Expectation Maximization (EM) gradient algorithm is proposed in order to tackle this challenge. The advantages of the spatial model and NIG distributions are evaluated with a cross-validation study based ondata from 14 patients. The study show that the proposed model enhances the predictive quality of the s-CT images by reducing the mean absolute error with 17.9%. Also, the distribution of CT values conditioned on the MR images are better explainedby the proposed model as evaluated using continuous ranked probability scores.

Ort, förlag, år, upplaga, sidor
2016. , s. 30
Nationell ämneskategori
Sannolikhetsteori och statistik Medicinsk bildbehandling
Forskningsämne
matematisk statistik
Identifikatorer
URN: urn:nbn:se:umu:diva-141566OAI: oai:DiVA.org:umu-141566DiVA, id: diva2:1155480
Forskningsfinansiär
Vetenskapsrådet, 340-2013-5342Knut och Alice Wallenbergs Stiftelse, 2008-5382Tillgänglig från: 2017-11-08 Skapad: 2017-11-08 Senast uppdaterad: 2018-06-09

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

arXiv:1607.02188

Personposter BETA

Johansson, AdamYu, Jun

Sök vidare i DiVA

Av författaren/redaktören
Johansson, AdamYu, Jun
Av organisationen
RadiofysikOnkologiInstitutionen för matematik och matematisk statistik
Sannolikhetsteori och statistikMedicinsk bildbehandling

Sök vidare utanför DiVA

GoogleGoogle Scholar

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 296 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf