MRI Reconstruction
In its most basic form, MRI reconstruction consists in retrieving a complex-valued image from its under-sampled Fourier coefficients. Besides, it can be addressed as a encoder-decoder task, in which the normative model in the latent space will only capture the relevant information without noise or corruptions. Then, we decode the latent space in order to have a reconstructed MRI.
Papers
Showing 1–10 of 441 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | HUMUS-Net (train+val data) | SSIM | 0.89 | — | Unverified |
| 2 | HUMUS-Net (train only) | SSIM | 0.89 | — | Unverified |
| 3 | End-to-end variational network | SSIM | 0.89 | — | Unverified |
| 4 | XPDNet | SSIM | 0.89 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | PromptMR | SSIM | 0.9 | — | Unverified |
| 2 | HUMUS-Net-L | SSIM | 0.9 | — | Unverified |
| 3 | HUMUS-Net | SSIM | 0.89 | — | Unverified |
| 4 | E2E-VarNet (train+val) | SSIM | 0.89 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | End-to-end variational network | SSIM | 0.96 | — | Unverified |
| 2 | XPDNet | SSIM | 0.96 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | End-to-end variational network | SSIM | 0.94 | — | Unverified |
| 2 | XPDNet | SSIM | 0.94 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | End-to-end variational network | SSIM | 0.93 | — | Unverified |
| 2 | XPDNet | SSIM | 0.93 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Residual U-NET | DSSIM | 0 | — | Unverified |