TY - JOUR
T1 - Deep learning-based parameter mapping for joint relaxation and diffusion tensor MR Fingerprinting
AU - Pirkl, Carolin M.
AU - Gómez, Pedro A.
AU - Lipp, Ilona
AU - Buonincontri, Guido
AU - Molina-Romero, Miguel
AU - Sekuboyina, Anjany
AU - Waldmannstetter, Diana
AU - Dannenberg, Jonathan
AU - Endt, Sebastian
AU - Merola, Alberto
AU - Whittaker, Joseph R.
AU - Tomassini, Valentina
AU - Tosetti, Michela
AU - Jones, Derek K.
AU - Menze, Bjoern H.
AU - Menzel, Marion I.
N1 - Publisher Copyright:
© 2020 C.M. Pirkl et al.
PY - 2020
Y1 - 2020
N2 - Magnetic Resonance Fingerprinting (MRF) enables the simultaneous quantification of multiple properties of biological tissues. It relies on a pseudo-random acquisition and the matching of acquired signal evolutions to a precomputed dictionary. However, the dictionary is not scalable to higher-parametric spaces, limiting MRF to the simultaneous mapping of only a small number of parameters (proton density, T1 and T2 in general). Inspired by diffusion-weighted SSFP imaging, we present a proof-of-concept of a novel MRF sequence with embedded diffusion-encoding gradients along all three axes to efficiently encode orientational diffusion and T1 and T2 relaxation. We take advantage of a convolutional neural network (CNN) to reconstruct multiple quantitative maps from this single, highly undersampled acquisition. We bypass expensive dictionary matching by learning the implicit physical relationships between the spatiotemporal MRF data and the T1, T2 and diffusion tensor parameters. The predicted parameter maps and the derived scalar diffusion metrics agree well with state-of-the-art reference protocols. Orientational diffusion information is captured as seen from the estimated primary diffusion directions. In addition to this, the joint acquisition and reconstruction framework proves capable of preserving tissue abnormalities in multiple sclerosis lesions.
AB - Magnetic Resonance Fingerprinting (MRF) enables the simultaneous quantification of multiple properties of biological tissues. It relies on a pseudo-random acquisition and the matching of acquired signal evolutions to a precomputed dictionary. However, the dictionary is not scalable to higher-parametric spaces, limiting MRF to the simultaneous mapping of only a small number of parameters (proton density, T1 and T2 in general). Inspired by diffusion-weighted SSFP imaging, we present a proof-of-concept of a novel MRF sequence with embedded diffusion-encoding gradients along all three axes to efficiently encode orientational diffusion and T1 and T2 relaxation. We take advantage of a convolutional neural network (CNN) to reconstruct multiple quantitative maps from this single, highly undersampled acquisition. We bypass expensive dictionary matching by learning the implicit physical relationships between the spatiotemporal MRF data and the T1, T2 and diffusion tensor parameters. The predicted parameter maps and the derived scalar diffusion metrics agree well with state-of-the-art reference protocols. Orientational diffusion information is captured as seen from the estimated primary diffusion directions. In addition to this, the joint acquisition and reconstruction framework proves capable of preserving tissue abnormalities in multiple sclerosis lesions.
KW - Convolutional Neural Network
KW - Diffusion Tensor
KW - Image Reconstruction
KW - Magnetic Resonance Fingerprinting
KW - Multiple Sclerosis
UR - http://www.scopus.com/inward/record.url?scp=85108881159&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85108881159
SN - 2640-3498
VL - 121
SP - 638
EP - 654
JO - Proceedings of Machine Learning Research
JF - Proceedings of Machine Learning Research
T2 - 3rd Conference on Medical Imaging with Deep Learning, MIDL 2020
Y2 - 6 July 2020 through 8 July 2020
ER -