Accelerating CEST imaging using a model-based deep neural network with synthetic training data

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Author(s)

  • Jianping Xu
  • Tao Zu
  • Yi-Cheng Hsu
  • Xiaoli Wang
  • Yi Zhang

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)583-599
Journal / PublicationMagnetic Resonance in Medicine
Volume91
Issue number2
Online published22 Oct 2023
Publication statusPublished - Feb 2024

Abstract

Purpose: To develop a model-based deep neural network for high-quality image reconstruction of undersampled multi-coil CEST data.
Theory and Methods: Inspired by the variational network (VN), the CEST image reconstruction equation is unrolled into a deep neural network (CEST-VN) with a k-space data-sharing block that takes advantage of the inherent redundancy in adjacent CEST frames and 3D spatial–frequential convolution kernels that exploit correlations in the x-ω domain. Additionally, a new pipeline based on multiple-pool Bloch–McConnell simulations is devised to synthesize multi-coil CEST data from publicly available anatomical MRI data. The proposed network is trained on simulated data with a CEST-specific loss function that jointly measures the structural and CEST contrast. The performance of CEST-VN was evaluated on four healthy volunteers and five brain tumor patients using retrospectively or prospectively undersampled data with various acceleration factors, and then compared with other conventional and state-of-the-art reconstruction methods.
Results: The proposed CEST-VN method generated high-quality CEST source images and amide proton transfer-weighted maps in healthy and brain tumor subjects, consistently outperforming GRAPPA, blind compressed sensing, and the original VN. With the acceleration factors increasing from 3 to 6, CEST-VN with the same hyperparameters yielded similar and accurate reconstruction without apparent loss of details or increase of artifacts. The ablation studies confirmed the effectiveness of the CEST-specific loss function and data-sharing block used.
Conclusions: The proposed CEST-VN method can offer high-quality CEST source images and amide proton transfer-weighted maps from highly undersampled multi-coil data by integrating the deep learning prior and multi-coil sensitivity encoding model.
© 2023 International Society for Magnetic Resonance in Medicine.

Research Area(s)

  • CEST, deep learning, fast MRI, image reconstruction, variational network

Citation Format(s)

Accelerating CEST imaging using a model-based deep neural network with synthetic training data. / Xu, Jianping; Zu, Tao; Hsu, Yi-Cheng et al.
In: Magnetic Resonance in Medicine, Vol. 91, No. 2, 02.2024, p. 583-599.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review