LSTM-Based RNN Framework to Remove Motion Artifacts in Dynamic Multicontrast MR Images with Registration Model

<div>Dataset of reduced motion artifacts obtained in the different image planes (axial, sagittal, and coronary). C1: motion-free MR image. C2: motion-blurred frames after mixing with zero padding. C3: WD and PD error output. C4: LSTM-based RNN output. C5: error mapping between C4 and C1.</div>

Wireless Communications and Mobile Computing

fig8

Figure 8

Figure 8: LSTM-Based RNN Framework to Remove Motion Artifacts in Dynamic Multicontrast MR Images with Registration Model 