# Abdominal trauma detection on Proprietary abdominal ultrasound video dataset (test)

Source: [Abdominal trauma detection on Proprietary abdominal ultrasound video dataset (test)](<https://www.sota2.com/research/sota/abdominal-trauma-detection-on-proprietary-abdominal-ultrasound-video-dataset-test>)

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

Data updated: 2026-06-29T07:01:04.408Z

Evaluation of abdominal trauma detection performance on the test split of the proprietary abdominal ultrasound video dataset, reporting Accuracy, Precision, Recall, F1-score, and Jaccard.

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 | Abdominal trauma detection |
| Dataset (including any stated split) | Proprietary abdominal ultrasound video dataset (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/abdominal-trauma-detection-on-proprietary-abdominal-ultrasound-video-dataset-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/abdominal-trauma-detection-on-proprietary-abdominal-ultrasound-video-dataset-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/abdominal-trauma-detection-on-proprietary-abdominal-ultrasound-video-dataset-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1-score](<https://www.sota2.com/research/sota/abdominal-trauma-detection-on-proprietary-abdominal-ultrasound-video-dataset-test.md?metric=F1-score>): Higher is better; unit: PERCENT.

- [Jaccard](<https://www.sota2.com/research/sota/abdominal-trauma-detection-on-proprietary-abdominal-ultrasound-video-dataset-test.md?metric=Jaccard>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TRUST | 83.34 | Not recorded | 6a41fc27206542251d7ccc2e |
| TRUST | 81.36 | Not recorded | 6a41fc27206542251d7ccc2e |
| VLPA-CLIP | 73.71 | Not recorded | 6a41fc27206542251d7ccc2e |
| Vita-CLIP | 71.06 | Not recorded | 6a41fc27206542251d7ccc2e |
| Surg-PEFT | 70.76 | Not recorded | 6a41fc27206542251d7ccc2e |
| AIM | 70.76 | Not recorded | 6a41fc27206542251d7ccc2e |
| M2-CLIP | 69.69 | Not recorded | 6a41fc27206542251d7ccc2e |
| AIM | 68.77 | Not recorded | 6a41fc27206542251d7ccc2e |
| VLPA-CLIP | 66.84 | Not recorded | 6a41fc27206542251d7ccc2e |
| ST-Adapter | 66.74 | Not recorded | 6a41fc27206542251d7ccc2e |
| Vita-CLIP | 66.63 | Not recorded | 6a41fc27206542251d7ccc2e |
| M2-CLIP | 65.56 | Not recorded | 6a41fc27206542251d7ccc2e |
| Surg-PEFT | 65.26 | Not recorded | 6a41fc27206542251d7ccc2e |
| ST-Adapter | 65 | Not recorded | 6a41fc27206542251d7ccc2e |

### TRUST

Accuracy: 83.34. Result ID: 6a421827fbc373592c86e41e.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

Recorded evaluation configuration: {"Frames":"8 × 2","Modal":"I+T"}. This record does not assert independent reproduction.

### TRUST

Accuracy: 81.36. Result ID: 6a421827fbc373592c86e417.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

Recorded evaluation configuration: {"Frames":"4 × 2","Modal":"I+T"}. This record does not assert independent reproduction.

### VLPA-CLIP

Accuracy: 73.71. Result ID: 6a421827fbc373592c86e41d.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

Recorded evaluation configuration: {"Frames":"8 × 2","Modal":"I+T"}. This record does not assert independent reproduction.

### Vita-CLIP

Accuracy: 71.06. Result ID: 6a421827fbc373592c86e41b.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f091e209131cea4374e.md>)

[Implementation](<https://github.com/TalalWasim/Vita-CLIP>)

Recorded evaluation configuration: {"Frames":"8 × 2","Modal":"I+T"}. This record does not assert independent reproduction.

### Surg-PEFT

Accuracy: 70.76. Result ID: 6a421827fbc373592c86e413.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75041e209131cea65483.md>)

Recorded evaluation configuration: {"Frames":"4 × 2","Modal":"I"}. This record does not assert independent reproduction.

### AIM

Accuracy: 70.76. Result ID: 6a421827fbc373592c86e419.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e801e209131cea405f5.md>)

[Implementation](<https://adapt-image-models.github.io/>)

Recorded evaluation configuration: {"Frames":"8 × 2","Modal":"I"}. This record does not assert independent reproduction.

### M2-CLIP

Accuracy: 69.69. Result ID: 6a421827fbc373592c86e415.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

Recorded evaluation configuration: {"Frames":"4 × 2","Modal":"I+T"}. This record does not assert independent reproduction.

### AIM

Accuracy: 68.77. Result ID: 6a421827fbc373592c86e412.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e801e209131cea405f5.md>)

[Implementation](<https://adapt-image-models.github.io/>)

Recorded evaluation configuration: {"Frames":"4 × 2","Modal":"I"}. This record does not assert independent reproduction.

### VLPA-CLIP

Accuracy: 66.84. Result ID: 6a421827fbc373592c86e416.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

Recorded evaluation configuration: {"Frames":"4 × 2","Modal":"I+T"}. This record does not assert independent reproduction.

### ST-Adapter

Accuracy: 66.74. Result ID: 6a421827fbc373592c86e418.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d9f1e209131cea3aeec.md>)

[Implementation](<https://github.com/linziyi96/st-adapter>)

Recorded evaluation configuration: {"Frames":"8 × 2","Modal":"I"}. This record does not assert independent reproduction.

### Vita-CLIP

Accuracy: 66.63. Result ID: 6a421827fbc373592c86e414.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f091e209131cea4374e.md>)

[Implementation](<https://github.com/TalalWasim/Vita-CLIP>)

Recorded evaluation configuration: {"Frames":"4 × 2","Modal":"I+T"}. This record does not assert independent reproduction.

### M2-CLIP

Accuracy: 65.56. Result ID: 6a421827fbc373592c86e41c.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

Recorded evaluation configuration: {"Frames":"8 × 2","Modal":"I+T"}. This record does not assert independent reproduction.

### Surg-PEFT

Accuracy: 65.26. Result ID: 6a421827fbc373592c86e41a.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75041e209131cea65483.md>)

Recorded evaluation configuration: {"Frames":"8 × 2","Modal":"I"}. This record does not assert independent reproduction.

### ST-Adapter

Accuracy: 65. Result ID: 6a421827fbc373592c86e411.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc27206542251d7ccc2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d9f1e209131cea3aeec.md>)

[Implementation](<https://github.com/linziyi96/st-adapter>)

Recorded evaluation configuration: {"Frames":"4 × 2","Modal":"I"}. This record does not assert independent reproduction.

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