Memory efficient model based deep learning reconstructions for high spatial resolution 3D non-cartesian acquisitions

Objective. Model based deep learning (MBDL) has been challenging to apply to the reconstruction of 3D non-Cartesian MRI due to GPU memory demand because the entire volume is needed for data-consistency steps embedded in the model. This requirement makes holding even a single unroll in GPU memory dif...

Descripción completa

Detalles Bibliográficos
Autores principales: Miller, Zachary, Pirasteh, Ali, Johnson, Kevin M
Formato: Online Artículo Texto
Lenguaje:English
Publicado: IOP Publishing 2023
Materias:
Paper
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10034748/
https://www.ncbi.nlm.nih.gov/pubmed/36854193
http://dx.doi.org/10.1088/1361-6560/acc003

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10034748/
https://www.ncbi.nlm.nih.gov/pubmed/36854193
http://dx.doi.org/10.1088/1361-6560/acc003

Ejemplares similares