Skip to main content
. Author manuscript; available in PMC: 2021 Jan 1.
Published in final edited form as: IEEE Signal Process Mag. 2020 Jan 17;37(1):111–127. doi: 10.1109/MSP.2019.2950433

Fig. 3.

Fig. 3.

Neural network architecture for MRI reconstruction. One residual block (ResBlock) [28] is illustrated in A with f feature maps. The ResBlock is used as a building block for the different networks. In B, one iteration of the reconstruction network is depicted where the i-th dataset is passed through the k-th iteration. Matrix Ai represents the imaging model, mi represents the dataset in the image domain, and yi represents the dataset in the k-space domain. The final output can be passed through the network in C to extract feature maps that can be compared to the feature maps extracted from the ground truth data using the same network. The tanh activation function in C is used to ensure that the values in the outputted feature maps are within ±1.