Synthesizing 4D Magnetic Resonance Angiography From 3D Time-of-Flight Using Deep Learning: A Feasibility Study.

Objective and background This study aimed to develop a deep convolutional neural network (DCNN) model capable of generating synthetic 4D magnetic resonance angiography (MRA) from 3D time-of-flight (TOF) images, allowing estimation of temporal changes in arterial flow. TOF MRA provides static information about arterial structures through maximum intensity projection (MIP) processing, but it does not capture the dynamic information of contrast agent circulation, which is lost during MIP processing. Considering the principles of TOF, it is hypothesized that dynamic information about arterial blood flow is latent within TOF signals. Although arterial spin labeling (ASL) can extract dynamic arterial information, ASL MRA has drawbacks, such as longer imaging times and lower spatial resolution than TOF MRA. This study's primary aim is to extend the utility of TOF MRA by training a machine-learning model on paired TOF and ASL data to extract latent dynamic information from TOF signals. Methods A DCNN combining a modified U-Net and a long-short-term memory (LSTM) network was trained on a dataset of 13 subjects (11 men and two women, aged 42-77 years) using paired 3D TOF MRA and 4D ASL MRA images. Subjects had no history of cerebral vessel occlusion or significant stenosis. The dataset was acquired using a 3T MRI system with a 32-channel head coil. Preprocessing involved resampling and intensity normalization of TOF and ASL images, followed by data augmentation and arterial mask generation. The model learned to extract flow information from TOF images and generate 8-phase 4D MRA images. The precision of flow estimation was evaluated using the coefficient of determination (R²) and Bland-Altman analysis. A board-certified neuroradiologist validated the quality of the images and the absence of significant stenosis in the major cerebral arteries. Results The generated 4D MRA images closely resembled the ground-truth ASL MRA data, with R² values of 0.92, 0.85, and 0.84 for the internal carotid artery (ICA), proximal middle cerebral artery (MCA), and distal MCA, respectively. Bland-Altman analysis revealed a systematic error of -0.06, with 95% agreement limits ranging from -0.18 to 0.12. Additionally, the model successfully identified flow abnormalities in a subject with left MCA stenosis, displaying a delayed peak and subsequent flattening distal to the stenosis, indicative of reduced blood flow. Visualization of the predicted arterial flow overlaid on the original TOF MRA images highlighted the spatial progression and dynamics of the flow. Conclusions The DCNN model effectively generated synthetic 4D MRA images from TOF images, demonstrating its potential to estimate temporal changes in arterial flow accurately. This non-invasive technique offers a promising alternative to conventional methods for visualizing and evaluating healthy and pathological flow dynamics. It has significant potential to improve the diagnosis and treatment of cerebrovascular diseases by providing detailed temporal flow information without the need for contrast agents or invasive procedures. The practical implementation of this model could enable the extraction of dynamic cerebral blood flow information from routine brain MRI examinations, contributing to the early diagnosis and management of cerebrovascular disorders.

Automation of a Rule-based Workflow to Estimate Age from Brain MR Imaging of Infants and Children Up to 2 Years Old Using Stacked Deep Learning.

PURPOSE: Myelination-related MR signal changes in white matter are helpful for assessing normal development in infants and children. A rule-based myelination evaluation workflow regarding signal changes on T1-weighted images (T1WIs) and T2-weighted images (T2WIs) has been widely used in radiology. This study aimed to simulate a rule-based workflow using a stacked deep learning model and evaluate age estimation accuracy. METHODS: The age estimation system involved two stacked neural networks: a target network-to extract five myelination-related images from the whole brain, and an age estimation network from extracted T1- and T2WIs separately. A dataset was constructed from 119 children aged below 2 years with two MRI systems. A four-fold cross-validation method was adopted. The correlation coefficient (CC), mean absolute error (MAE), and root mean squared error (RMSE) of the corrected chronological age of full-term birth, as well as the mean difference and the upper and lower limits of 95% agreement, were measured. Generalization performance was assessed using datasets acquired from different MR images. Age estimation was performed in Sturge-Weber syndrome (SWS) cases. RESULTS: There was a strong correlation between estimated age and corrected chronological age (MAE: 0.98 months; RMSE: 1.27 months; and CC: 0.99). The mean difference and standard deviation (SD) were -0.15 and 1.26, respectively, and the upper and lower limits of 95% agreement were 2.33 and -2.63 months. Regarding generalization performance, the performance values on the external dataset were MAE of 1.85 months, RMSE of 2.59 months, and CC of 0.93. Among 13 SWS cases, 7 exceeded the limits of 95% agreement, and a proportional bias of age estimation based on myelination acceleration was exhibited below 12 months of age (P = 0.03). CONCLUSION: Stacked deep learning models automated the rule-based workflow in radiology and achieved highly accurate age estimation in infants and children up to 2 years of age.

Effect of Temporal Sampling Rate on Estimates of the Perfusion Parameters for Patients with Moyamoya Disease Assessed with Simultaneous Multislice Dynamic Susceptibility Contrast-enhanced MR Imaging.

PURPOSE: The effect of temporal sampling rate (TSR) on perfusion parameters has not been fully investigated in Moyamoya disease (MMD); therefore, this study evaluated the influence of different TSRs on perfusion parameters quantitatively and qualitatively by applying simultaneous multi-slice (SMS) dynamic susceptibility contrast-enhanced MR imaging (DSC-MRI). METHODS: DSC-MRI datasets were acquired from 28 patients with MMD with a TSR of 0.5 s. Cerebral blood flow (CBF), cerebral blood volume (CBV), mean transit time (MTT), time to peak (TTP), and time to maximum tissue residue function (Tmax) were calculated for eight TSRs ranging from 0.5 to 4.0 s in 0.5-s increments that were subsampled from a TSR of 0.5 s datasets. Perfusion measurements and volume for chronic ischemic (Tmax ≥ 2 s) and non-ischemic (Tmax < 2 s) areas for each TSR were compared to measurements with a TSR of 0.5 s, as was visual perfusion map analysis. RESULTS: CBF, CBV, and Tmax values tended to be underestimated, whereas MTT and TTP values were less influenced, with a longer TSR. Although Tmax values were overestimated in the TSR of 1.0 s in non-ischemic areas, differences in perfusion measurements between the TSRs of 0.5 and 1.0 s were generally minimal. The volumes of the chronic ischemic areas with a TSR ≥ 3.0 s were significantly underestimated. In CBF and CBV maps, no significant deterioration was noted in image quality up to 3.0 and 2.5 s, respectively. The image quality of MTT, TTP, and Tmax maps for the TSR of 1.0 s was similar to that for the TSR of 0.5 s but was significantly deteriorated for the TSRs of ≥ 1.5 s. CONCLUSION: In the assessment of MMD by SMS DSC-MRI, application of TSRs of ≥ 1.5 s may lead to deterioration of the perfusion measurements; however, that was less influenced in TSRs of ≤ 1.0 s.

Evaluation of white matter microstructure in patients with Parkinson's disease using microscopic fractional anisotropy.

PURPOSE: Micro fractional anisotropy (µFA) is more accurate than conventional fractional anisotropy (FA) for assessing microscopic tissue properties and can overcome limitations related to crossing white matter fibres. We compared µFA and FA for evaluating white matter changes in patients with Parkinson's disease (PD). METHODS: We compared FA and µFA measures between 25 patients with PD and 25 age- and gender-matched healthy controls using tract-based spatial statistics (TBSS) analysis. We also examined potential correlations between changes, revealed by conventional FA or µFA, and disease duration or Unified Parkinson's Disease Rating Scale (UPDRS)-III scores. RESULTS: Compared with healthy controls, patients with PD had significantly reduced µFA values, mainly in the anterior corona radiata (ACR). In the PD group, µFA values (primarily those from the ACR) were significantly negatively correlated with UPDRS-III motor scores. No significant changes or correlations with disease duration or UPDRS-III scores with tissue properties were detected using conventional FA. CONCLUSION: µFA can evaluate microstructural changes that occur during white matter degeneration in patients with PD and may overcome a key limitation of FA.