2021-07-26科研进展

The words in blue are the knowledge points involved in the presentation
In preprocessing stage：
First, the original data is preprocessed using zero-padding
Then the fully sampled original data is accelerated to obtain the undersampled data
In order to perform the accelerated operation, we need to design a 4-fold accelerated sampling mask
In reconstruction：
Input undersampled data，output reconstructed data，and then calculate loss error between reconstructed data and original fully sampled data
Whole flow of reconstruction network structure。CNN performs operations in the image domain in order to extract features。Data consistency deals with k-space Data
Finally is PSNR，SSIM

This