Magnetic resonance imaging
-
To improve the signal-to-noise ratio (SNR) and image sharpness for whole brain isotropic 0.5 mm three-dimensional (3D) T1 weighted (T1w) turbo spin echo (TSE) intracranial vessel wall imaging (IVWI) at 3 T. ⋯ The CNN enhanced VFA TSE imaging enables an overall image quality improvement for high-resolution 3D T1w IVWI, and may provide a better tradeoff across scan efficiency, SNR and PSF for 3D TSE acquisitions.
-
Deep brain stimulation (DBS) has become a widely performed surgical procedure for patients with medically refractory movement disorders and mental disorders. It is clinically important to set up a MRI protocol to map the brain targets and electrodes of the patients before and after DBS and to understand the imaging artifacts caused by the electrodes. ⋯ The imaging protocol consisting of MPRAGE T1W, FSE T2W and ME-GRE sequences provided excellent pre- and post-operative visualization of the brain targets and electrodes for patients undergoing DBS treatment. Although the artifacts around the electrodes can be severe, sometimes these same artifacts can be useful in identifying their location.
-
To evaluate the performance of novel spiral MRSI and tissue segmentation pipeline of the brain, to investigate neurometabolic changes in normal-appearing white matter (NAWM) and white matter lesions (WML) of stable relapsing remitting multiple sclerosis (RRMS) compared to healthy controls (HCs). ⋯ This study demonstrates the benefit of MRSI in evaluating MS neurometabolic changes in NAWM. SVM of MRSI data in the MS brain may be suited for clinical monitoring and progression of MS patients. Longitudinal MRSI studies are warranted.
-
To develop and evaluate a deep adversarial learning-based image reconstruction approach for rapid and efficient MR parameter mapping. ⋯ The proposed framework by incorporating the efficient end-to-end CNN mapping, adversarial learning, and physical model enforced data consistency is a promising approach for rapid and efficient reconstruction of quantitative MR parameters.
-
To develop a fast and accurate convolutional neural network based method for segmentation of thalamic nuclei. ⋯ The proposed segmentation method is fast, accurate, performs well across disease types and field strengths, and shows great potential for improving our understanding of thalamic nuclei involvement in neurological diseases.