Fig. 7 | Scientific Reports

Fig. 7

From: Complex-valued neural networks to speed-up MR thermometry during hyperthermia using Fourier PD and PDUNet

Fig. 7

Comparison of the reconstruction quality achieved by the complex-valued models-Fourier-PDNet and Fourier-PDUNet-and the real-valued model ReconResNet with two types of inputs-real and imaginary, and magnitude and phase-as well as the zero-padded k-space (denoted as undersampled) for k-space undersampled using 1D variable density sampling taking 25% of the k-space. SSIM values for (A) magnitude and (B) phase.

Back to article page