Accelerating Chemical Exchange Saturation Transfer Imaging Using a Model-based Deep Neural Network With Synthetic Training Data

TL;DR

This paper introduces a model-based deep neural network called CEST-VN that accelerates chemical exchange saturation transfer imaging by reconstructing high-quality images from highly undersampled data using synthetic training data and advanced neural network architecture.

Contribution

The paper presents a novel deep neural network architecture for CEST image reconstruction that leverages synthetic data and a variational network-inspired design, improving speed and quality over existing methods.

Findings

CEST-VN outperforms GRAPPA, compressed sensing, and variational network in image quality.

Maintains accuracy and detail at acceleration factors up to 6.

Effective use of synthetic training data and CEST-specific loss function.

Abstract

Purpose: To develop a model-based deep neural network for high-quality image reconstruction of undersampled multi-coil chemical exchange saturation transfer (CEST) data. Theory and Methods: Inspired by the variational network, 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-{\omega} 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 neural 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 three healthy volunteers and five brain tumor patients using retrospectively undersampled data with various acceleration factors, and compared with other state-of-the-art reconstruction methods. Results: The proposed CEST-VN method generated high-quality CEST source images and APT-weighted (APTw) maps in healthy and brain tumor subjects, consistently outperforming GRAPPA, blind compressed sensing, and the original variational network. 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 joint CEST-specific loss function and data-sharing block used. Conclusions: The proposed CEST-VN method can offer high-quality CEST source images and APTw maps from highly undersampled multi-coil data by integrating the deep-learning prior and multi-coil sensitivity encoding model.