@inproceedings{GolbabaeeChenGomezetal.2019, author = {Golbabaee, Mohammad and Chen, Dongdong and G{\´o}mez, Pedro A. and Menzel, Marion Irene and Davies, Mike E.}, title = {Geometry of Deep Learning for Magnetic Resonance Fingerprinting}, booktitle = {ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-5386-4658-8}, doi = {https://doi.org/10.1109/ICASSP.2019.8683549}, pages = {7825 -- 7829}, year = {2019}, language = {en} } @inproceedings{ChenGolbabaeeGomezetal.2019, author = {Chen, Dongdong and Golbabaee, Mohammad and G{\´o}mez, Pedro A. and Menzel, Marion Irene and Davies, Mike E.}, title = {Deep Fully Convolutional Network for MR Fingerprinting}, booktitle = {Medical Imaging with Deep Learning, MIDL 2019: Extended Abstract Track}, editor = {Cardoso, M. Jorge and Feragen, Aasa and Glocker, Ben and Konukoglu, Ender and Oguz, Ipek and Unal, Gozde and Vercauteren, Tom}, url = {https://openreview.net/forum?id=SJxUdvJTtN}, year = {2019}, abstract = {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.}, language = {en} } @inproceedings{GolbabaeeChenDaviesetal.2019, author = {Golbabaee, Mohammad and Chen, Dongdong and Davies, Mike E. and Menzel, Marion Irene and G{\´o}mez, Pedro A.}, title = {Spatio-temporal regularization for deep MR Fingerprinting}, booktitle = {Medical Imaging with Deep Learning, MIDL 2019: Extended Abstract Track}, editor = {Cardoso, M. Jorge and Feragen, Aasa and Glocker, Ben and Konukoglu, Ender and Oguz, Ipek and Unal, Gozde and Vercauteren, Tom}, url = {https://openreview.net/forum?id=ryx64UL6YE}, year = {2019}, abstract = {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.}, language = {en} } @unpublished{ChenGolbabaeeGomezetal.2019, author = {Chen, Dongdong and Golbabaee, Mohammad and G{\´o}mez, Pedro A. and Menzel, Marion Irene and Davies, Mike E.}, title = {A Fully Convolutional Network for MR Fingerprinting}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.1911.09846}, year = {2019}, language = {en} }