Deep-Learning-Based Accelerated and Noise-Suppressed Estimation (DANSE) of quantitative Gradient Recalled Echo (qGRE) MRI metrics associated with Human Brain Neuronal Structure and Hemodynamic Properties

Abstract

Purpose: To introduce a Deep-Learning-Based Accelerated and Noise-Suppressed Estimation (DANSE) method for reconstructing quantitative maps of biological tissue cellular-specific, and hemodynamic-specific, from Gradient-Recalled-Echo (GRE) MRI data with multiple gradient-recalled echoes. Methods: DANSE method adapts supervised learning paradigm to train a convolutional neural network for robust estimation of and maps free from the adverse effects of macroscopic (B0) magnetic field inhomogeneities directly from the GRE magnitude images without utilizing phase images. The corresponding ground-truth maps were generated by means of a voxel-by-voxel fitting of a previously-developed biophysical quantitative GRE (qGRE) model accounting for tissue, hemodynamic and -inhomogeneities contributions to GRE signal with multiple gradient echoes using nonlinear least square (NLLS) algorithm. Results: We show that the DANSE model efficiently estimates the aforementioned brain maps and preserves all features of NLLS approach with significant improvements including noise-suppression and computation speed (from many hours to seconds). The noise-suppression feature of DANSE is especially prominent for data with SNR characteristic for typical GRE data (SNR~50), where DANSE-generated and maps had three times smaller errors than that of NLLS method. Conclusions: DANSE method enables fast reconstruction of magnetic-field-inhomogeneity-free and noise-suppressed quantitative qGRE brain maps. DANSE method does not require any information about field inhomogeneities during application. It exploits spatial patterns in the qGRE MRI data and previously-gained knowledge from the biophysical model, thus producing clean brain maps even in the environments with high noise levels. These features along with fast computational speed can lead to broad qGRE clinical and research applications.

CoRRECT: A Deep Unfolding Framework for Motion-Corrected Quantitative R2* Mapping

“…The training can be guided by minimizing the loss between the outputs of the DNN and the qMRI maps estimated from the MR images using standard fitting methods. This end-to-end mapping strategy has been investigated in several qMRI applications, including T 2 [51], high quality susceptibility mapping (QSM) [52,53], T 1 and T 1ρ [54], R2t * and R2 [55]. It has also been applied to help magnetic resonance fingerprinting (MRF) [56] with a better and more efficient generation of qMRI maps such as T 1 and T 2 [57,58].…”