Journal: NeuroImage

Article Title: Improved cortical surface reconstruction using sub-millimeter resolution MPRAGE by image denoising

doi: 10.1016/j.neuroimage.2021.117946

Figure Lengend Snippet: A representative axial image slice from the 6-repetition averaged data (a, i), the single-repetition data (a, ii), and the single-repetition data denoised by DnCNN (a, iii), BM4D (a, iv) and AONLM (a, v), along with magnified views of basal ganglia (row b). The arrowheads highlight the boundary of gray matter and white matter (green), the claustrum (blue), and the blood vessel in the internal capsule (magenta). The difference maps (row c) and the structural similarity index (SSIM) maps (row d) depict the similarity between the images from the single-repetition data and the denoised data compared to the images from the 6-repetition averaged data. SSIM scores range between 0 and 1, with larger values indicating higher similarity. The whole-brain mean absolute difference (MAD), mean peak signal-to-noise ratio (PSNR) and mean SSIM are used to quantify the image similarity.

Article Snippet: PSNR was computed using MATLAB’s “ psnr ” function, with larger value indicating lower mean squared error.

Techniques:

Journal: NeuroImage

Article Title: Improved cortical surface reconstruction using sub-millimeter resolution MPRAGE by image denoising

doi: 10.1016/j.neuroimage.2021.117946

Figure Lengend Snippet: The blue dots and error bars represent the group mean and standard deviation of the whole-brain mean absolute difference (MAD) (a), peak signal-to-noise ratio (PSNR) (b) and structural similarity index (SSIM) (c) of the images from the single-repetition data and 2- to 5-repetition averaged data compared to the images from the 6-repetition averaged data across 30 image volumes from the 5 evaluation subjects. The green, red and yellow dots and error bars represent the group mean and standard deviation of the MAD, PSNR and SSIM of the images from the single-repetition data denoised by DnCNN (green), BM4D (red) and AONLM (yellow) compared to the images from the 6-repetition averaged data across 30 image volumes from the 5 evaluation subjects. The red dots and error bars for BM4D are virtually covered by the yellow dots and error bars for AONLM. The numbers above and below the dashed lines that link two neighboring blue dots indicate the number of image volumes for averaging that would be needed to obtain equivalent similarity metrics to those obtained from images from single-repetition data denoised by different methods. All comparisons of results from different denoising methods and numbers of repetitions for averaging are statistically significant ( p <0.05), except for between the BM4D- and AONLM-denoised data for SSIM (c) (denoted with abbreviation “ns”).

Article Snippet: PSNR was computed using MATLAB’s “ psnr ” function, with larger value indicating lower mean squared error.

Techniques: Standard Deviation