From: Artifact-free fat-water separation in Dixon MRI using deep learning
Model | Water | Fat | ||
---|---|---|---|---|
SSIM | PSNR (dB) | SSIM | PSNR (dB) | |
\(IP\rightarrow \hat{F},\hat{W}\) | 0.926Â \({\pm }\)Â 0.010 | 24.77Â \({\pm }\)Â 0.73 | 0.949Â \({\pm }\)Â 0.008 | 25.22Â \({\pm }\)Â 0.79 |
\(IP,OP\rightarrow \hat{F},\hat{W}\) | 0.967Â \({\pm }\)Â 0.005 | 29.47Â \({\pm }\)Â 0.86 | 0.977Â \({\pm }\)Â 0.004 | 29.74Â \({\pm }\)Â 0.91 |
\(IP,OP\rightarrow \hat{F},\hat{W}\) | 0.939Â \({\pm }\)Â 0.008 | 26.48Â \({\pm }\)Â 0.90 | 0.953Â \({\pm }\)Â 0.007 | 26.73Â \({\pm }\)Â 0.92 |
(Dixon generator loss) |