Deformation equivariant cross-modality image synthesis with paired non-aligned training data
Loading...
Access rights
openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
2023-12
Department
Major/Subject
Mcode
Degree programme
Language
en
Pages
13
Series
Medical Image Analysis, Volume 90, pp. 1-13
Abstract
Cross-modality image synthesis is an active research topic with multiple medical clinically relevant applications. Recently, methods allowing training with paired but misaligned data have started to emerge. However, no robust and well-performing methods applicable to a wide range of real world data sets exist. In this work, we propose a generic solution to the problem of cross-modality image synthesis with paired but non-aligned data by introducing new deformation equivariance encouraging loss functions. The method consists of joint training of an image synthesis network together with separate registration networks and allows adversarial training conditioned on the input even with misaligned data. The work lowers the bar for new clinical applications by allowing effortless training of cross-modality image synthesis networks for more difficult data sets.Description
Funding Information: This work was supported by Research Council of Finland (Flagship programme: Finnish Center for Artificial Intelligence [grant 345552 ] and grants 315896 , 335976 , 336033 , 341967 , 352986 , 358246 ), ERA PerMed ABCAP (Research Council of Finland grants 334774 , 334782 ), EU (H2020 grant 101016775 and NextGenerationEU). We also acknowledge the computational resources provided by the Aalto Science-IT Project. | openaire: EC/H2020/101016775/EU//INTERVENE
Keywords
Cross-modality image synthesis, Image registration, Image-to-image translation
Other note
Citation
Honkamaa, J, Khan, U, Koivukoski, S, Valkonen, M, Latonen, L, Ruusuvuori, P & Marttinen, P 2023, ' Deformation equivariant cross-modality image synthesis with paired non-aligned training data ', Medical Image Analysis, vol. 90, 102940, pp. 1-13 . https://doi.org/10.1016/j.media.2023.102940