Motion‐tolerant diffusion mapping based on single‐shot overlapping‐echo detachment (OLED) planar imaging

Abstract

As a reliable fast diffusion measurement tool, DM-OLED shows promise for real-time dynamic diffusion mapping and functional magnetic resonance imaging. Magn Reson Med 80:200-210, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Single‐shot T2 mapping using overlapping‐echo detachment planar imaging and a deep convolutional neural network

“…The expanded images are shown in Figure . We can see that the reconstructed T 2 mappings from echo‐detachment‐based method show much more noise (regular noise‐like artifacts) and blurring around the texture edges, which can also be found in our previous works . This indicates the difficulty of denoising and reducing blurring effect at the same time for echo‐detachment‐based method.…”

“…Equation can be solved by using iterative reconstruction method. Detail of the echo‐detachment‐based method can be found in literature …”

“…Detail of the echodetachment-based method can be found in literature. 11,18 However, because of the texture variability in real experimental objects, the echo-detachment-based OLED reconstruction method may not be able to separate the overlapping-echo signals effectively by using a single objective function with some prior terms. Furthermore, the reconstruction of T 2 mapping, but not the separation of overlapping-echo signals, is the final goal.…”

“…Detailed simulation procedure can be found in our previous study. 29 As demonstrated in our early works, 11,18 the double-SE signal should be removed by a simple Gauss filter before the training and testing. We only normalized the amplitude of each full FOV input image, and did not normalize the label.…”

“…The trace starts at the three-o'clock position of the circle and runs counter-clockwise detachment-based method show much more noise (regular noise-like artifacts) and blurring around the texture edges, which can also be found in our previous works. 11,18 This indicates the difficulty of denoising and reducing blurring effect at the same time for echo-detachment-based method. However, ResNet method simultaneously achieves both quite well, and the results show good agreement with the reference T 2 mappings.…”