# Medical Re-identification on CXR NIH14 (internal)

Source: [Medical Re-identification on CXR NIH14 (internal)](<https://www.sota2.com/research/sota/medical-re-identification-on-cxr-nih14-internal>)

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

Data updated: 2026-06-23T09:03:11.723Z

Evaluation of Medical Re-identification performance using R1 and mAP metrics on the internal version of the CXR NIH14 dataset.

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 | Medical Re-identification |
| Dataset (including any stated split) | CXR NIH14 (internal) |
| Metric | R1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [R1](<https://www.sota2.com/research/sota/medical-re-identification-on-cxr-nih14-internal.md?metric=R1>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/medical-re-identification-on-cxr-nih14-internal.md?metric=mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | R1 | Result date | Report paper |
| --- | --- | --- | --- |
| Full (Graph-of-Differences) | 90.33 | Not recorded | 6a3a1341206542251d7c71b5 |
| Backbone-only | 87.23 | Not recorded | 6a3a1341206542251d7c71b5 |
| Backbone + Graph (w/o Ldiff) | 86.59 | Not recorded | 6a3a1341206542251d7c71b5 |

### Full (Graph-of-Differences)

R1: 90.33. Result ID: 6a3a4bbdfbc373592c355e95.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1341206542251d7c71b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a1341206542251d7c71b5.md>)

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

### Backbone-only

R1: 87.23. Result ID: 6a3a4bbdfbc373592c355e93.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1341206542251d7c71b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73041.md>)

[Implementation](<https://github.com/tianyuan168326/All-in-One-MedReID-Pytorch>)

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

### Backbone + Graph (w/o Ldiff)

R1: 86.59. Result ID: 6a3a4bbdfbc373592c355e94.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a1341206542251d7c71b5.md>)

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

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