A1 Vertaisarvioitu alkuperäisartikkeli tieteellisessä lehdessä
Deformation equivariant cross-modality image synthesis with paired non-aligned training data
Tekijät: Honkamaa Joel, Khan Umair, Koivukoski Sonja, Valkonen Mira, Latonen Leena, Ruusuvuori Pekka, Marttinen Pekka
Julkaisuvuosi: 2023
Journal: Medical Image Analysis
Tietokannassa oleva lehden nimi: Medical image analysis
Lehden akronyymi: Med Image Anal
Artikkelin numero: 102940
Vuosikerta: 90
ISSN: 1361-8415
eISSN: 1361-8423
DOI: https://doi.org/10.1016/j.media.2023.102940
Rinnakkaistallenteen osoite: https://research.utu.fi/converis/portal/detail/Publication/180886342
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.
Ladattava julkaisu This is an electronic reprint of the original article. |  |
