Harmonisation of scanner-dependent contrast variations in magnetic resonance imaging for radiation oncology, using style-blind auto-encoders

BACKGROUND AND PURPOSE: Magnetic Resonance Imaging (MRI) exhibits scanner dependent contrast, which limits generalisability of radiomics and machine-learning for radiation oncology. Current deep-learning harmonisation requires paired data, retraining for new scanners and often suffers from geometry-...

Descripción completa

Detalles Bibliográficos
Autores principales: Fatania, Kavi, Clark, Anna, Frood, Russell, Scarsbrook, Andrew, Al-Qaisieh, Bashar, Currie, Stuart, Nix, Michael
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Article(s) from the Special Issue on Physics highlights from ESTRO 2021
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9127401/
https://www.ncbi.nlm.nih.gov/pubmed/35619643
http://dx.doi.org/10.1016/j.phro.2022.05.005

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9127401/
https://www.ncbi.nlm.nih.gov/pubmed/35619643
http://dx.doi.org/10.1016/j.phro.2022.05.005

Ejemplares similares