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-...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Kavi Fatania, Anna Clark, Russell Frood, Andrew Scarsbrook, Bashar Al-Qaisieh, Stuart Currie, Michael Nix
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Elsevier 2022-04-01
coleção:	Physics and Imaging in Radiation Oncology
Assuntos:	Magnetic Resonance Imaging (MRI) harmonisation Image translation Oncology Deep-learning Radiomics
Acesso em linha:	http://www.sciencedirect.com/science/article/pii/S2405631622000458
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!