Original title: Unfolded Low-rank + Sparse Reconstruction for MRI
Authors: Mokrý, O. ; Vitouš, Jiří
Document type: Papers
Conference/Event: STUDENT EEICT 2022 /28./, Brno (CZ), 20220426
Year: 2022
Language: eng
Abstract: 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.
Keywords: DCE-MRI; deep unfolding; L+S model; proximal splitting algorithms
Host item entry: Proceedings II of the 28th Conference STUDENT EEICT 2022. Selected Papers, ISBN 978-80-214-6030-0, ISSN 2788-1334

Institution: Institute of Scientific Instruments AS ČR (web)
Document availability information: Fulltext is available at external website.
External URL: https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2022_sbornik_2_v3.pdf
Original record: https://hdl.handle.net/11104/0340114

Permalink: http://www.nusl.cz/ntk/nusl-521042


The record appears in these collections:
Research > Institutes ASCR > Institute of Scientific Instruments
Conference materials > Papers