# Diagnostic Classification on SIIM-ACR Pneumothorax

Source: [Diagnostic Classification on SIIM-ACR Pneumothorax](<https://www.sota2.com/research/sota/diagnostic-classification-on-siim-acr-pneumothorax>)

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

Data updated: 2026-05-26T07:17:58.963Z

Evaluation of diagnostic classification performance on the SIIM-ACR Pneumothorax dataset, reporting AUROC scores calculated using varying percentages of labeled data (1%, 10%, 100%).

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 | Diagnostic Classification |
| Dataset (including any stated split) | SIIM-ACR Pneumothorax |
| Metric | AUROC (1% labels) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [AUROC (1% labels)](<https://www.sota2.com/research/sota/diagnostic-classification-on-siim-acr-pneumothorax.md?metric=AUROC%20(1%25%20labels)>): Higher is better; unit: PERCENT.

- [AUROC (10% labels)](<https://www.sota2.com/research/sota/diagnostic-classification-on-siim-acr-pneumothorax.md?metric=AUROC%20(10%25%20labels)>): Higher is better; unit: PERCENT.

- [AUROC (100% labels)](<https://www.sota2.com/research/sota/diagnostic-classification-on-siim-acr-pneumothorax.md?metric=AUROC%20(100%25%20labels)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AUROC (1% labels) | Result date | Report paper |
| --- | --- | --- | --- |
| GazeWorld | 87.85 | Not recorded | 6a152902dbd7150506f7ddd4 |
| EGMA | 87.17 | Not recorded | 6a152902dbd7150506f7ddd4 |
| MGCA | 86.14 | Not recorded | 6a152902dbd7150506f7ddd4 |
| MedCLIP | 86.09 | Not recorded | 6a152902dbd7150506f7ddd4 |
| PRIOR | 81.96 | Not recorded | 6a152902dbd7150506f7ddd4 |
| MedKLIP | 74.5 | Not recorded | 6a152902dbd7150506f7ddd4 |
| BioViL | 62.98 | Not recorded | 6a152902dbd7150506f7ddd4 |
| CheXWorld | 62.31 | Not recorded | 6a152902dbd7150506f7ddd4 |

### GazeWorld

AUROC (1% labels): 87.85. Result ID: 6a1548f9fbc373592c0c34f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised classification","Backbone Status":"frozen"}. This record does not assert independent reproduction.

### EGMA

AUROC (1% labels): 87.17. Result ID: 6a1548f9fbc373592c0c34f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a61e209131cea5daca.md>)

[Implementation](<https://github.com/Momarky/EGMA>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised classification","Backbone Status":"frozen"}. This record does not assert independent reproduction.

### MGCA

AUROC (1% labels): 86.14. Result ID: 6a1548f9fbc373592c0c34f1.

[Reporting paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d9e1e209131cea3ae0a.md>)

[Implementation](<https://github.com/fuying-wang/MGCA>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised classification","Backbone Status":"frozen"}. This record does not assert independent reproduction.

### MedCLIP

AUROC (1% labels): 86.09. Result ID: 6a1548f9fbc373592c0c34f4.

[Reporting paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da91e209131cea3b45b.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised classification","Backbone Status":"frozen"}. This record does not assert independent reproduction.

### PRIOR

AUROC (1% labels): 81.96. Result ID: 6a1548f9fbc373592c0c34f2.

[Reporting paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56560.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised classification","Backbone Status":"frozen"}. This record does not assert independent reproduction.

### MedKLIP

AUROC (1% labels): 74.5. Result ID: 6a1548f9fbc373592c0c34f0.

[Reporting paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised classification","Backbone Status":"frozen"}. This record does not assert independent reproduction.

### BioViL

AUROC (1% labels): 62.98. Result ID: 6a1548f9fbc373592c0c34ef.

[Reporting paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72491e209131cea55961.md>)

[Implementation](<https://aka.ms/biovil-t-code>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised classification","Backbone Status":"frozen"}. This record does not assert independent reproduction.

### CheXWorld

AUROC (1% labels): 62.31. Result ID: 6a1548f9fbc373592c0c34f3.

[Reporting paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78201e209131cea76e60.md>)

[Implementation](<https://github.com/LeapLabTHU/CheXWorld>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised classification","Backbone Status":"frozen"}. This record does not assert independent reproduction.

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