Browsing by Subject "Diffusion Magnetic Resonance Imaging"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Denoising diffusion weighted imaging data using convolutional neural networks
    (Public Library of Science, 2022-09-15) Cheng, Hu; Vinci-Booher, Sophia; Wang, Jian; Caron, Bradley; Wen, Qiuting; Newman, Sharlene; Pestilli, Franco; Radiology and Imaging Sciences, School of Medicine
    Diffusion weighted imaging (DWI) with multiple, high b-values is critical for extracting tissue microstructure measurements; however, high b-value DWI images contain high noise levels that can overwhelm the signal of interest and bias microstructural measurements. Here, we propose a simple denoising method that can be applied to any dataset, provided a low-noise, single-subject dataset is acquired using the same DWI sequence. The denoising method uses a one-dimensional convolutional neural network (1D-CNN) and deep learning to learn from a low-noise dataset, voxel-by-voxel. The trained model can then be applied to high-noise datasets from other subjects. We validated the 1D-CNN denoising method by first demonstrating that 1D-CNN denoising resulted in DWI images that were more similar to the noise-free ground truth than comparable denoising methods, e.g., MP-PCA, using simulated DWI data. Using the same DWI acquisition but reconstructed with two common reconstruction methods, i.e. SENSE1 and sum-of-square, to generate a pair of low-noise and high-noise datasets, we then demonstrated that 1D-CNN denoising of high-noise DWI data collected from human subjects showed promising results in three domains: DWI images, diffusion metrics, and tractography. In particular, the denoised images were very similar to a low-noise reference image of that subject, more than the similarity between repeated low-noise images (i.e. computational reproducibility). Finally, we demonstrated the use of the 1D-CNN method in two practical examples to reduce noise from parallel imaging and simultaneous multi-slice acquisition. We conclude that the 1D-CNN denoising method is a simple, effective denoising method for DWI images that overcomes some of the limitations of current state-of-the-art denoising methods, such as the need for a large number of training subjects and the need to account for the rectified noise floor.
  • Thumbnail Image
    Item
    Perturbed neurochemical and microstructural organization in a mouse model of prenatal opioid exposure: A multi-modal magnetic resonance study
    (Public Library of Science, 2023-07-20) Shahid, Syed Salman; Grecco, Gregory G.; Atwood, Brady K.; Wu, Yu-Chien; Radiology and Imaging Sciences, School of Medicine
    Methadone-based treatment for pregnant women with opioid use disorder is quite prevalent in the clinical environment. A number of clinical and animal model-based studies have reported cognitive deficits in infants prenatally exposed to methadone-based opioid treatments. However, the long-term impact of prenatal opioid exposure (POE) on pathophysiological mechanisms that govern neurodevelopmental impairment is not well understood. Using a translationally relevant mouse model of prenatal methadone exposure (PME), the aim of this study is to investigate the role of cerebral biochemistry and its possible association with regional microstructural organization in PME offspring. To understand these effects, 8-week-old male offspring with PME (n = 7) and prenatal saline exposure (PSE) (n = 7) were scanned in vivo on 9.4 Tesla small animal scanner. Single voxel proton magnetic resonance spectroscopy (1H-MRS) was performed in the right dorsal striatum (RDS) region using a short echo time (TE) Stimulated Echo Acquisition Method (STEAM) sequence. Neurometabolite spectra from the RDS was first corrected for tissue T1 relaxation and then absolute quantification was performed using the unsuppressed water spectra. High-resolution in vivo diffusion MRI (dMRI) for region of interest (ROI) based microstructural quantification was also performed using a multi-shell dMRI sequence. Cerebral microstructure was characterized using diffusion tensor imaging (DTI) and Bingham-neurite orientation dispersion and density imaging (Bingham-NODDI). MRS results in the RDS showed significant decrease in N-acetyl aspartate (NAA), taurine (tau), glutathione (GSH), total creatine (tCr) and glutamate (Glu) concentration levels in PME, compared to PSE group. In the same RDS region, mean orientation dispersion index (ODI) and intracellular volume fraction (VFIC) demonstrated positive associations with tCr in PME group. ODI also exhibited significant positive association with Glu levels in PME offspring. Significant reduction in major neurotransmitter metabolites and energy metabolism along with strong association between the neurometabolites and perturbed regional microstructural complexity suggest a possible impaired neuroadaptation trajectory in PME offspring which could be persistent even into late adolescence and early adulthood.
  • Thumbnail Image
    Item
    Super-Resolution Diffusion Tensor Imaging using SRCNN: A Feasibility Study*
    (IEEE Xplore, 2019-07-27) Elsaid, Nahla M. H.; Wu, Yu-Chien; Radiology and Imaging Sciences, School of Medicine
    High-resolution diffusion imaging with submillimeter isotropic voxels requires long scan times that are usually clinically impractical. Even with those long scans, the image quality can still suffer from low signal-to-noise ratio (SNR) and severe geometric distortion due to long echo spacing in echo-planar imaging sequences. In this study, we proposed and validated the efficacy of using a stateof-the-art deep-learning method, super-resolution convolutional neural network (SRCNN), to achieve submillimeter super-resolution diffusion-weighted (DW) images. The 2D-based deep-learning method was validated by comparing with the ground truth using numerical simulations and by studying region-of-interest (ROI) using real human data of three healthy volunteers. Furthermore, we interrogated the proposed method under different real-life SNR conditions. The results demonstrated that the proposed deep- learning method was able to reproduce sufficient details in the anatomy that can only be detected using high-resolution diffusion imaging. The percentage errors in diffusion tensor imaging (DTI) derived metrics were less than 8% when the baseline SNR larger than 20. The ROI results demonstrated that the proposed method produced comparable values of diffusion metrics to the matched high-resolution diffusion metrics of real human data. Particularly, the patterns of distributions of the subjects were similar between the proposed method and real data across wholebrain gray-matter and white-matter ROIs. A deep-learned submillimeter resolution of 0.625 mm diffusion directional image showed high image quality, particularly in the cortical gray matter. We demonstrated the feasibility of using a deep-learning algorithm based on SRCNN in DTI. This approach can be a robust alternative when acquiring the true sub-millimeter diffusion MRI is not available.