TY - CHAP A1 - Golbabaee, Mohammad A1 - Chen, Dongdong A1 - Gómez, Pedro A. A1 - Menzel, Marion Irene A1 - Davies, Mike E. T1 - Geometry of Deep Learning for Magnetic Resonance Fingerprinting T2 - ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) UR - https://doi.org/10.1109/ICASSP.2019.8683549 KW - magnetic resonance fingerprinting KW - inverse problem KW - deep learning KW - dictionary KW - manifold compressed sensing Y1 - 2019 UR - https://doi.org/10.1109/ICASSP.2019.8683549 SN - 978-1-5386-4658-8 SP - 7825 EP - 7829 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Chen, Dongdong A1 - Golbabaee, Mohammad A1 - Gómez, Pedro A. A1 - Menzel, Marion Irene A1 - Davies, Mike E. ED - Cardoso, M. Jorge ED - Feragen, Aasa ED - Glocker, Ben ED - Konukoglu, Ender ED - Oguz, Ipek ED - Unal, Gozde ED - Vercauteren, Tom T1 - Deep Fully Convolutional Network for MR Fingerprinting T2 - Medical Imaging with Deep Learning, MIDL 2019: Extended Abstract Track N2 - This work proposes an end-to-end deep fully convolutional neural network for MRF reconstruction (MRF-FCNN), which firstly employs linear dimensionality reduction and then uses a neural network to project the data into the tissue parameters. The MRF dictionary is only used for training the network and not during image reconstruction. We show that MRF-FCNN is capable of achieving accuracy comparable to the ground-truth maps thanks to capturing spatio-temporal data structures without a need for the non-scalable dictionary matching step used in the baseline reconstructions. KW - Magnetic Resonance Fingerprinting KW - Deep Learning Y1 - 2019 UR - https://openreview.net/forum?id=SJxUdvJTtN UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-31163 ER - TY - CHAP A1 - Golbabaee, Mohammad A1 - Chen, Dongdong A1 - Davies, Mike E. A1 - Menzel, Marion Irene A1 - Gómez, Pedro A. ED - Cardoso, M. Jorge ED - Feragen, Aasa ED - Glocker, Ben ED - Konukoglu, Ender ED - Oguz, Ipek ED - Unal, Gozde ED - Vercauteren, Tom T1 - Spatio-temporal regularization for deep MR Fingerprinting T2 - Medical Imaging with Deep Learning, MIDL 2019: Extended Abstract Track N2 - We study a deep learning approach to address the heavy storage and computation re- quirements of the baseline dictionary-matching (DM) for Magnetic Resonance Fingerprint- ing (MRF) reconstruction. The MRF-Net provides a piece-wise affine approximation to the (temporal) Bloch response manifold projection. Fed with non-iterated back-projected images, the network alone is unable to fully resolve spatially-correlated artefacts which ap- pear in highly undersampling regimes. We propose an accelerated iterative reconstruction to minimize these artefacts before feeding into the network. This is done through a convex regularization that jointly promotes spatio-temporal regularities of the MRF time-series. KW - magnetic resonance fingerprinting KW - deep learning KW - regularisation Y1 - 2019 UR - https://openreview.net/forum?id=ryx64UL6YE UR - https://2019.midl.io/program/extended-abstracts.html UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-31174 ER - TY - INPR A1 - Chen, Dongdong A1 - Golbabaee, Mohammad A1 - Gómez, Pedro A. A1 - Menzel, Marion Irene A1 - Davies, Mike E. T1 - A Fully Convolutional Network for MR Fingerprinting UR - https://doi.org/10.48550/arXiv.1911.09846 Y1 - 2019 UR - https://doi.org/10.48550/arXiv.1911.09846 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Golbabaee, Mohammad A1 - Chen, Dongdong A1 - Gómez, Pedro A. A1 - Menzel, Marion Irene A1 - Davies, Mike E. T1 - Geometry of Deep Learning for Magnetic Resonance Fingerprinting UR - https://doi.org/10.48550/arXiv.1809.01749 Y1 - 2018 UR - https://doi.org/10.48550/arXiv.1809.01749 PB - arXiv CY - Ithaca ER -