Umeå University's logo

umu.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
Denoising and uncertainty estimation in parameter mapping with approximate Bayesian deep image priors
Umeå University, Faculty of Medicine, Department of Radiation Sciences.ORCID iD: 0000-0002-0200-6567
Umeå University, Faculty of Medicine, Department of Radiation Sciences. Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0001-7119-7646
Umeå University, Faculty of Medicine, Department of Radiation Sciences.ORCID iD: 0000-0002-0532-232X
2023 (English)In: Magnetic Resonance in Medicine, ISSN 0740-3194, E-ISSN 1522-2594, Vol. 90, no 6, p. 2557-2571Article in journal (Refereed) Published
Abstract [en]

Purpose: To mitigate the problem of noisy parameter maps with high uncertainties by casting parameter mapping as a denoising task based on Deep Image Priors.

Methods: We extend the concept of denoising with Deep Image Prior (DIP) into parameter mapping by treating the output of an image-generating network as a parametrization of tissue parameter maps. The method implicitly denoises the parameter mapping process by filtering low-level image features with an untrained convolutional neural network (CNN). Our implementation includes uncertainty estimation from Bernoulli approximate variational inference, implemented with MC dropout, which provides model uncertainty in each voxel of the denoised parameter maps. The method is modular, so the specifics of different applications (e.g., T1 mapping) separate into application-specific signal equation blocks. We evaluate the method on variable flip angle T1 mapping, multi-echo T2 mapping, and apparent diffusion coefficient mapping.

Results: We found that deep image prior adapts successfully to several applications in parameter mapping. In all evaluations, the method produces noise-reduced parameter maps with decreased uncertainty compared to conventional methods. The downsides of the proposed method are the long computational time and the introduction of some bias from the denoising prior.

Conclusion: DIP successfully denoise the parameter mapping process and applies to several applications with limited hyperparameter tuning. Further, it is easy to implement since DIP methods do not use network training data. Although time-consuming, uncertainty information from MC dropout makes the method more robust and provides useful information when properly calibrated.

Place, publisher, year, edition, pages
John Wiley & Sons, 2023. Vol. 90, no 6, p. 2557-2571
Keywords [en]
deep image prior, denoising, parameter mapping, quantitative MRI, uncertainty estimation
National Category
Medical Image Processing Computer graphics and computer vision
Identifiers
URN: urn:nbn:se:umu:diva-213711DOI: 10.1002/mrm.29823ISI: 001049833500001PubMedID: 37582257Scopus ID: 2-s2.0-85168117341OAI: oai:DiVA.org:umu-213711DiVA, id: diva2:1797466
Funder
Swedish Research Council, 2019‐0432Region Västerbotten, RV‐970119Cancerforskningsfonden i Norrland, AMP 18‐912Available from: 2023-09-14 Created: 2023-09-14 Last updated: 2025-02-01Bibliographically approved

Open Access in DiVA

fulltext(7926 kB)94 downloads
File information
File name FULLTEXT02.pdfFile size 7926 kBChecksum SHA-512
6a664aa5b6aaa1420d6e185bc0dea47dd7ce8918e56549c3a182e4e34a86f23ec816dc428c1f4ee0d6a61804a7935f94f9b70c1f1c030c967f5641493d745ea7
Type fulltextMimetype application/pdf

Other links

Publisher's full textPubMedScopus

Authority records

Hellström, MaxLöfstedt, TommyGarpebring, Anders

Search in DiVA

By author/editor
Hellström, MaxLöfstedt, TommyGarpebring, Anders
By organisation
Department of Radiation SciencesDepartment of Computing Science
In the same journal
Magnetic Resonance in Medicine
Medical Image ProcessingComputer graphics and computer vision

Search outside of DiVA

GoogleGoogle Scholar
Total: 131 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: 287 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