Improved multi-echo gradient echo myelin water fraction mapping using complex-valued neural network analysis.

PURPOSE: Previously, an artificial neural network method was introduced to estimate quantitative myelin water fraction (MWF) using multi-echo gradient-echo data. However, the fiber orientation of white matter with respect to B0 could bias the quantification of MWF. Here, we developed an advanced workflow for MWF estimation that could improve the quantification of MWF. METHODS: To adopt fiber orientation effects, a complex-valued neural network with complex-valued operation was used. In addition, to compensate for the bias from different scan parameters, a signal model incorporating the T1 value was devised for training data generation. At the testing stage, a voxel-spread function approach was utilized for spatial B0 artifact correction. Finally, dropout-based variational inference was implemented for uncertainty estimates on the network model to provide a confidence interpretation of the output. RESULTS: According to simulation and in vivo analysis, the proposed method suggests improved quality of MWF estimation by correcting the bias and artifacts. The proposed complex-valued neural network approach can alleviate the dependency of fiber orientation effects compared to previous artificial neural network method. Uncertainty estimates provides information different from fitting error that can be used as a confidence level of the resulting MWF values. CONCLUSION: An improved MWF mapping using complex-valued neural network analysis has been proposed.

Improving phase-based conductivity reconstruction by means of deep learning-based denoising of B1+ phase data for 3T MRI.

PURPOSE: To denoise B1+ phase using a deep learning method for phase-based in vivo electrical conductivity reconstruction in a 3T MR system. METHODS: For B1+ phase deep-learning denoising, a convolutional neural network (U-net) was chosen. Training was performed on data sets from 10 healthy volunteers. Input data were the real and imaginary components of single averaged spin-echo data (SNR = 45), which was used to approximate the B1+ phase. For label data, multiple signal-averaged spin-echo data (SNR = 128) were used. Testing was performed on in silico and in vivo data. Reconstructed conductivity maps were derived using phase-based conductivity reconstructions. Additionally, we investigated the usability of the network to various SNR levels, imaging contrasts, and anatomical sites (ie, T1 , T2 , and proton density-weighted brain images and proton density-weighted breast images. In addition, conductivity reconstructions from deep learning-based denoised data were compared with conventional image filters, which were used for data denoising in electrical properties tomography (ie, the Gaussian filtering and the Savitzky-Golay filtering). RESULTS: The proposed deep learning-based denoising approach showed improvement for B1+ phase for both in silico and in vivo experiments with reduced quantitative error measures compared with other methods. Subsequently, this resulted in an improvement of reconstructed conductivity maps from the denoised B1+ phase with deep learning. CONCLUSION: The results suggest that the proposed approach can be used as an alternative preprocessing method to denoise B1+ maps for phase-based conductivity reconstruction without relying on image filters or signal averaging.

Artificial neural network for multi-echo gradient echo-based myelin water fraction estimation.

PURPOSE: To demonstrate robust myelin water fraction (MWF) mapping using an artificial neural network (ANN) with multi-echo gradient-echo (GRE) signal. METHODS: Multi-echo gradient-echo signals simulated with a three-pool exponential model were used to generate the training data set for the ANN, which was designed to yield the MWF. We investigated the performance of our proposed ANN for various conditions using both numerical simulations and in vivo data. Simulations were conducted with various SNRs to investigate the performance of the ANN. In vivo data with high spatial resolutions were applied in the analyses, and results were compared with MWFs derived by the nonlinear least-squares algorithm using a complex three-pool exponential model. RESULTS: The network results for the simulations show high accuracies against noise compared with nonlinear least-squares MWFs: RMS-error value of 5.46 for the nonlinear least-squares MWF and 3.56 for the ANN MWF at an SNR of 150 (relative gain = 34.80%). These effects were also found in the in vivo data, with reduced SDs in the region-of-interest analyses. These effects of the ANN demonstrate the feasibility of acquiring high-resolution myelin water images. CONCLUSION: The simulation results and in vivo data suggest that the ANN facilitates more robust MWF mapping in multi-echo gradient-echo sequences compared with the conventional nonlinear least-squares method.