# Healthy Anatomy Reconstruction on AIBL T1w MRI (601/67)

Source: [Healthy Anatomy Reconstruction on AIBL T1w MRI (601/67)](<https://www.sota2.com/research/sota/healthy-anatomy-reconstruction-on-aibl-t1w-mri-601-67>)

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

Data updated: 2026-02-26T05:47:59.429Z

Evaluation of model performance in reconstructing healthy anatomical structures from AIBL T1w MRI scans (601/67 subset), assessed using L1 loss, PSNR, and SSIM.

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 | Healthy Anatomy Reconstruction |
| Dataset (including any stated split) | AIBL T1w MRI (601/67) |
| Metric | L1 Loss |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [L1 Loss](<https://www.sota2.com/research/sota/healthy-anatomy-reconstruction-on-aibl-t1w-mri-601-67.md?metric=L1%20Loss>): Lower is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/healthy-anatomy-reconstruction-on-aibl-t1w-mri-601-67.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/healthy-anatomy-reconstruction-on-aibl-t1w-mri-601-67.md?metric=SSIM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | L1 Loss | Result date | Report paper |
| --- | --- | --- | --- |
| Brain-ID | 0.009 | Not recorded | 68fa76ab1e209131cea6e4f1 |
| UNA | 0.01 | Not recorded | 68fa76ab1e209131cea6e4f1 |
| PEPSI | 0.012 | Not recorded | 68fa76ab1e209131cea6e4f1 |
| SynthSR | 0.026 | Not recorded | 68fa76ab1e209131cea6e4f1 |

### Brain-ID

L1 Loss: 0.009. Result ID: 69945d003a6c3148491cc153.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ab1e209131cea6e4f1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72721e209131cea565d0.md>)

Recorded evaluation configuration: {"Input Modality":"T1w MRI"}. This record does not assert independent reproduction.

### UNA

L1 Loss: 0.01. Result ID: 69945d003a6c3148491cc155.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ab1e209131cea6e4f1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ab1e209131cea6e4f1.md>)

[Implementation](<https://github.com/peirong26/UNA>)

Recorded evaluation configuration: {"Input Modality":"T1w MRI"}. This record does not assert independent reproduction.

### PEPSI

L1 Loss: 0.012. Result ID: 69945d003a6c3148491cc154.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ab1e209131cea6e4f1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72741e209131cea56710.md>)

[Implementation](<https://github.com/peirong26/PEPSI>)

Recorded evaluation configuration: {"Input Modality":"T1w MRI"}. This record does not assert independent reproduction.

### SynthSR

L1 Loss: 0.026. Result ID: 69945d003a6c3148491cc152.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ab1e209131cea6e4f1.md>)

Recorded evaluation configuration: {"Input Modality":"T1w MRI"}. This record does not assert independent reproduction.

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