DeepCEST 7 T: Fast and homogeneous mapping of 7 T CEST MRI parameters and their uncertainty quantification
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
DeepCEST 7 T : Fast and homogeneous mapping of 7 T CEST MRI parameters and their uncertainty quantification. / Hunger, Leonie; Rajput, Junaid R.; Klein, Kiril; Mennecke, Angelika; Fabian, Moritz S.; Schmidt, Manuel; Glang, Felix; Herz, Kai; Liebig, Patrick; Nagel, Armin M.; Scheffler, Klaus; Doerfler, Arnd; Maier, Andreas; Zaiss, Moritz.
In: Magnetic Resonance in Medicine, Vol. 89, No. 4, 2023, p. 1543-1556.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - DeepCEST 7 T
T2 - Fast and homogeneous mapping of 7 T CEST MRI parameters and their uncertainty quantification
AU - Hunger, Leonie
AU - Rajput, Junaid R.
AU - Klein, Kiril
AU - Mennecke, Angelika
AU - Fabian, Moritz S.
AU - Schmidt, Manuel
AU - Glang, Felix
AU - Herz, Kai
AU - Liebig, Patrick
AU - Nagel, Armin M.
AU - Scheffler, Klaus
AU - Doerfler, Arnd
AU - Maier, Andreas
AU - Zaiss, Moritz
PY - 2023
Y1 - 2023
N2 - Purpose In this work, we investigated the ability of neural networks to rapidly and robustly predict Lorentzian parameters of multi-pool CEST MRI spectra at 7 T with corresponding uncertainty maps to make them quickly and easily available for routine clinical use. Methods We developed a deepCEST 7 T approach that generates CEST contrasts from just 1 scan with robustness against B-1 inhomogeneities. The input data for a neural feed-forward network consisted of 7 T in vivo uncorrected Z-spectra of a single B-1 level, and a B-1 map. The 7 T raw data were acquired using a 3D snapshot gradient echo multiple interleaved mode saturation CEST sequence. These inputs were mapped voxel-wise to target data consisting of Lorentzian amplitudes generated conventionally by 5-pool Lorentzian fitting of normalized, denoised, B-0- and B-1-corrected Z-spectra. The deepCEST network was trained with Gaussian negative log-likelihood loss, providing an uncertainty quantification in addition to the Lorentzian amplitudes. Results The deepCEST 7 T network provides fast and accurate prediction of all Lorentzian parameters also when only a single B-1 level is used. The prediction was highly accurate with respect to the Lorentzian fit amplitudes, and both healthy tissues and hyperintensities in tumor areas are predicted with a low uncertainty. In corrupted cases, high uncertainty indicated wrong predictions reliably. Conclusion The proposed deepCEST 7 T approach reduces scan time by 50% to now 6:42 min, but still delivers both B-0- and B-1-corrected homogeneous CEST contrasts along with an uncertainty map, which can increase diagnostic confidence. Multiple accurate 7 T CEST contrasts are delivered within seconds.
AB - Purpose In this work, we investigated the ability of neural networks to rapidly and robustly predict Lorentzian parameters of multi-pool CEST MRI spectra at 7 T with corresponding uncertainty maps to make them quickly and easily available for routine clinical use. Methods We developed a deepCEST 7 T approach that generates CEST contrasts from just 1 scan with robustness against B-1 inhomogeneities. The input data for a neural feed-forward network consisted of 7 T in vivo uncorrected Z-spectra of a single B-1 level, and a B-1 map. The 7 T raw data were acquired using a 3D snapshot gradient echo multiple interleaved mode saturation CEST sequence. These inputs were mapped voxel-wise to target data consisting of Lorentzian amplitudes generated conventionally by 5-pool Lorentzian fitting of normalized, denoised, B-0- and B-1-corrected Z-spectra. The deepCEST network was trained with Gaussian negative log-likelihood loss, providing an uncertainty quantification in addition to the Lorentzian amplitudes. Results The deepCEST 7 T network provides fast and accurate prediction of all Lorentzian parameters also when only a single B-1 level is used. The prediction was highly accurate with respect to the Lorentzian fit amplitudes, and both healthy tissues and hyperintensities in tumor areas are predicted with a low uncertainty. In corrupted cases, high uncertainty indicated wrong predictions reliably. Conclusion The proposed deepCEST 7 T approach reduces scan time by 50% to now 6:42 min, but still delivers both B-0- and B-1-corrected homogeneous CEST contrasts along with an uncertainty map, which can increase diagnostic confidence. Multiple accurate 7 T CEST contrasts are delivered within seconds.
KW - amide
KW - CEST
KW - deep learning
KW - neural networks
KW - rNOE
KW - uncertainty quantification
KW - SATURATION
KW - PROVIDES
U2 - 10.1002/mrm.29520
DO - 10.1002/mrm.29520
M3 - Journal article
C2 - 36377762
VL - 89
SP - 1543
EP - 1556
JO - Magnetic Resonance in Medicine
JF - Magnetic Resonance in Medicine
SN - 0740-3194
IS - 4
ER -
ID: 327068579