A CVAE-based generative model for generalized B1 inhomogeneity corrected chemical exchange saturation transfer MRI at 5 T

Chemical exchange saturation transfer (CEST) magnetic resonance imaging (MRI) has emerged as a powerful tool to image endogenous or exogenous macromolecules. CEST contrast highly depends on radiofrequency irradiation B1 level. Spatial inhomogeneity of B1 field would bias CEST measurement. Convention...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	NeuroImage (Orlando, Fla.) Jg. 312; S. 121202
Hauptverfasser:	Zhang, Ruifen, Zhang, Qiyang, Wu, Yin
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Inc 15.05.2025 Elsevier
Schlagworte:	B1 inhomogeneity Chemical exchange saturation transfer (CEST) Conditional variational autoencoder (CVAE) Chemical exchange saturation transfer (CEST) Conditional variational autoencoder (CVAE) B1 inhomogeneity
ISSN:	1053-8119, 1095-9572, 1095-9572
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Chemical exchange saturation transfer (CEST) magnetic resonance imaging (MRI) has emerged as a powerful tool to image endogenous or exogenous macromolecules. CEST contrast highly depends on radiofrequency irradiation B1 level. Spatial inhomogeneity of B1 field would bias CEST measurement. Conventional interpolation-based B1 correction method required CEST dataset acquisition under multiple B1 levels, substantially prolonging scan time. The recently proposed supervised deep learning approach reconstructed B1 inhomogeneity corrected CEST effect at the identical B1 as of the training data, hindering its generalization to other B1 levels. In this study, we proposed a Conditional Variational Autoencoder (CVAE)-based generative model to generate B1 inhomogeneity corrected Z spectra from single CEST acquisition. The model was trained from pixel-wise source–target paired Z spectra under multiple B1 with target B1 as a conditional variable. Numerical simulation and healthy human brain imaging at 5 T were respectively performed to evaluate the performance of proposed model in B1 inhomogeneity corrected CEST MRI. Results showed that the generated B1-corrected Z spectra agreed well with the reference averaged from regions with subtle B1 inhomogeneity. Moreover, the performance of the proposed model in correcting B1 inhomogeneity in APT CEST effect, as measured by both MTRasym and MTRRex at 3.5 ppm, were superior over conventional Z/contrast-B1-interpolation and other deep learning methods, especially when target B1 were not included in sampling or training dataset. In summary, the proposed model allows generalized B1 inhomogeneity correction, benefiting quantitative CEST MRI in clinical routines. [Display omitted] •The proposed method enables generalized B1 inhomogeneity correction for CEST MRI, improving clinical feasibility.•The method corrects B1 inhomogeneity from a single CEST acquisition, reducing scan time.•The method outperforms interpolation and other deep learning methods, even for untrained B1 levels.
Bibliographie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1053-8119 1095-9572 1095-9572
DOI:	10.1016/j.neuroimage.2025.121202