kth.sePublications
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
Multi-Scale Learned Iterative Reconstruction
Univ Oulu, Res Unit Math Sci, FIN-90570 Oulu, Finland.;UCL, Dept Comp Sci, London W E 6BT, England..
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematics (Div.). Elekta, S-11357 Stockholm, Sweden.;DeepMind, London N1C 4AG, England..ORCID iD: 0000-0001-9928-3407
UCL, Dept Comp Sci, London W E 6BT, England..ORCID iD: 0000-0003-1292-0210
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.).ORCID iD: 0000-0002-1118-6483
2020 (English)In: IEEE Transactions on Computational Imaging, ISSN 2573-0436, E-ISSN 2333-9403, Vol. 6, p. 843-856Article in journal (Refereed) Published
Abstract [en]

Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction algorithms. Applicability of these methods to large scale inverse problems is however limited by the available memory for training and extensive training times, the latter due to computationally expensive forward models. As a possible solution to these restrictions we propose a multi-scale learned iterative reconstruction scheme that computes iterates on discretisations of increasing resolution. This procedure does not only reduce memory requirements, it also considerably speeds up reconstruction and training times, but most importantly is scalable to large scale inverse problems with non-trivial forward operators, such as those that arise in many 3D tomographic applications. In particular, we propose a hybrid network that combines the multi-scale iterative approach with a particularly expressive network architecture which in combination exhibits excellent scalability in 3D. Applicability of the algorithm is demonstrated for 3D cone beam computed tomography from real measurement data of an organic phantom. Additionally, we examine scalability and reconstruction quality in comparison to established learned reconstruction methods in two dimensions for low dose computed tomography on human phantoms.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2020. Vol. 6, p. 843-856
Keywords [en]
Model-based learning, iterative reconstruction, cone beam computed tomography, deep learning, inverse problems
National Category
Clinical Medicine
Identifiers
URN: urn:nbn:se:kth:diva-291062DOI: 10.1109/TCI.2020.2990299ISI: 000615034700001PubMedID: 33644260Scopus ID: 2-s2.0-85095037981OAI: oai:DiVA.org:kth-291062DiVA, id: diva2:1532504
Note

QC 20210302.

QC 20210318.

Available from: 2021-03-02 Created: 2021-03-02 Last updated: 2022-06-25Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Adler, JonasÖktem, Ozan

Search in DiVA

By author/editor
Adler, JonasArridge, SimonÖktem, Ozan
By organisation
Mathematics (Div.)Mathematics (Dept.)
In the same journal
IEEE Transactions on Computational Imaging
Clinical Medicine

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 376 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