An imaging-based method of mapping multi-echo BOLD intracranial pulsatility.

PURPOSE: Cardiac-related intracranial pulsatility may relate to cerebrovascular health, and this information is contained in BOLD MRI data. There is broad interest in methods to isolate BOLD pulsatility, and the current study examines a deep learning approach. METHODS: Multi-echo BOLD images, respiratory, and cardiac recordings were measured in 55 adults. Ground truth BOLD pulsatility maps were calculated with an established method. BOLD fast Fourier transform magnitude images were used as temporal-frequency image inputs to a U-Net deep learning model. Model performance was evaluated by mean squared error (MSE), mean absolute error (MAE), structural similarity index (SSIM), and mutual information (MI). Experiments evaluated the influence of input channel size, an age group effect during training, dependence on TE, performance without the U-Net architecture, and importance of respiratory preprocessing. RESULTS: The U-Net model generated BOLD pulsatility maps with lower MSE as additional fast Fourier transform input images were used. There was no age group effect for MSE (P > 0.14). MAE and SSIM metrics did not vary across TE (P > 0.36), whereas MI showed a significant TE dependence (P < 0.05). The U-Net versus no U-Net comparison showed no significant difference for MAE (P = 0.059); however, SSIM and MI were significantly different between models (P < 0.001). Within the insula, the cross-correlation values were high (r > 0.90) when comparing the U-Net model trained with/without respiratory preprocessing. CONCLUSION: Multi-echo BOLD pulsatility maps were synthesized from a U-net model that was trained to use temporal-frequency BOLD image inputs. This work adds to the deep learning methods that characterize BOLD physiological signals.

Characterization and correction of time-varying eddy currents for diffusion MRI.

PURPOSE: To develop and test a method for reducing artifacts due to time-varying eddy currents in oscillating gradient spin-echo (OGSE) diffusion images. METHODS: An in-house algorithm (TVEDDY), that for the first time retrospectively models eddy current decay, was tested on pulsed gradient spin echo and OGSE brain images acquired at 7 T. Image pairs were acquired using opposite polarity diffusion gradients. A three-parameter exponential decay model (two amplitudes and a time constant) was used to characterize and correct eddy current distortions by minimizing the intensity difference between image pairs. Correction performance was compared with conventional correction methods by evaluating the mean squared error (MSE) between diffusion-weighted images acquired with opposite polarity diffusion gradients. As a ground-truth comparison, images were corrected using field dynamics up to third order in space, measured using a field monitoring system. RESULTS: Time-varying eddy currents were observed for OGSE, which introduced blurring that was not reduced using the traditional approach but was diminished considerably with TVEDDY and field monitoring-informed model-based reconstruction. No MSE difference was observed between the conventional approach and TVEDDY for pulsed gradient spin echo, but for OGSE TVEDDY resulted in significantly lower MSE than the conventional approach. The field-monitoring reconstruction had the lowest MSE for both pulsed gradient spin echo and OGSE. CONCLUSION: This work establishes that it is possible to estimate time-varying eddy currents from the actual diffusion data, which provides substantial image-quality improvements for gradient-intensive diffusion MRI acquisitions like OGSE.