# MRI Reconstruction on Stanford Knee Cross-Center (test)

Source: [MRI Reconstruction on Stanford Knee Cross-Center (test)](<https://www.sota2.com/research/sota/mri-reconstruction-on-stanford-knee-cross-center-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-17T08:10:12.689Z

Evaluation of MRI reconstruction performance on the test split of the Stanford Knee Cross-Center dataset, measured using image quality metrics like PSNR, SSIM, and LPIPS.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | MRI reconstruction |
| Dataset (including any stated split) | Stanford Knee Cross-Center (test) |
| Metric | PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [PSNR](<https://www.sota2.com/research/sota/mri-reconstruction-on-stanford-knee-cross-center-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/mri-reconstruction-on-stanford-knee-cross-center-test.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/mri-reconstruction-on-stanford-knee-cross-center-test.md?metric=LPIPS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| BiasRecon | 31.29 | Not recorded | 69b8e00c0636e5bf4afbea46 |
| ConvDecoder | 30.84 | Not recorded | 69b8e00c0636e5bf4afbea46 |
| MoDL | 30.66 | Not recorded | 69b8e00c0636e5bf4afbea46 |
| DDS | 29.23 | Not recorded | 69b8e00c0636e5bf4afbea46 |
| TV | 24.12 | Not recorded | 69b8e00c0636e5bf4afbea46 |
| Zero-filling | 19.51 | Not recorded | 69b8e00c0636e5bf4afbea46 |

### BiasRecon

PSNR: 31.29. Result ID: 69b90c3147f34ce924a16c85.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00c0636e5bf4afbea46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e00c0636e5bf4afbea46.md>)

Recorded evaluation configuration: {"acceleration":"8x","sampling":"Gaussian 1D","category":"External deep image prior"}. This record does not assert independent reproduction.

### ConvDecoder

PSNR: 30.84. Result ID: 69b90c3147f34ce924a16c82.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00c0636e5bf4afbea46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d71e209131cea24839.md>)

Recorded evaluation configuration: {"acceleration":"8x","sampling":"Gaussian 1D","category":"Internal deep image prior"}. This record does not assert independent reproduction.

### MoDL

PSNR: 30.66. Result ID: 69b90c3147f34ce924a16c83.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00c0636e5bf4afbea46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65d71e209131cea0caa8.md>)

Recorded evaluation configuration: {"acceleration":"8x","sampling":"Gaussian 1D","category":"Supervised Method"}. This record does not assert independent reproduction.

### DDS

PSNR: 29.23. Result ID: 69b90c3147f34ce924a16c84.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00c0636e5bf4afbea46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72371e209131cea55039.md>)

Recorded evaluation configuration: {"acceleration":"8x","sampling":"Gaussian 1D","category":"External deep image prior"}. This record does not assert independent reproduction.

### TV

PSNR: 24.12. Result ID: 69b90c3147f34ce924a16c81.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00c0636e5bf4afbea46.md>)

Recorded evaluation configuration: {"acceleration":"8x","sampling":"Gaussian 1D","category":"Conventional CS method"}. This record does not assert independent reproduction.

### Zero-filling

PSNR: 19.51. Result ID: 69b90c3147f34ce924a16c80.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00c0636e5bf4afbea46.md>)

Recorded evaluation configuration: {"acceleration":"8x","sampling":"Gaussian 1D"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.