Název:
Unfolded Low-rank + Sparse Reconstruction for MRI
Autoři:
Mokrý, O. ; Vitouš, Jiří Typ dokumentu: Příspěvky z konference Konference/Akce: STUDENT EEICT 2022 /28./, Brno (CZ), 20220426
Rok:
2022
Jazyk:
eng
Abstrakt: We apply the methodology of deep unfolding on the problem of reconstruction of DCE-MRI data. The problem is formulated as a convex optimization problem, solvable via the primal-dual splitting algorithm. The unfolding allows for optimal hyperparameter selection for the model. We examine two approaches - with the parameters shared across the layers/iterations, and an adaptive version where the parameters can differ. The results demonstrate that the more complex model can better adapt to the data.
Klíčová slova:
DCE-MRI; deep unfolding; L+S model; proximal splitting algorithms Zdrojový dokument: Proceedings II of the 28th Conference STUDENT EEICT 2022. Selected Papers, ISBN 978-80-214-6030-0, ISSN 2788-1334