# Ultrasound Diagnosis on Liver

Source: [Ultrasound Diagnosis on Liver](<https://www.sota2.com/research/sota/ultrasound-diagnosis-on-liver>)

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

Data updated: 2026-05-22T07:17:43.111Z

Evaluation of Ultrasound Diagnosis performance on the Liver dataset, utilizing metrics such as SAcc, Alignment score, ECE, and Gap.

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 | Ultrasound Diagnosis |
| Dataset (including any stated split) | Liver |
| Metric | SAcc |
| Unit | PERCENT |
| 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

- [SAcc](<https://www.sota2.com/research/sota/ultrasound-diagnosis-on-liver.md?metric=SAcc>): Higher is better; unit: PERCENT.

- [Alignment Score](<https://www.sota2.com/research/sota/ultrasound-diagnosis-on-liver.md?metric=Alignment%20Score>): Higher is better; unit: PERCENT.

- [ECE](<https://www.sota2.com/research/sota/ultrasound-diagnosis-on-liver.md?metric=ECE>): Lower is better; unit: PERCENT.

- [Gap](<https://www.sota2.com/research/sota/ultrasound-diagnosis-on-liver.md?metric=Gap>): Lower is better; unit: SCALAR.

## Recorded results

| Method | SAcc | Result date | Report paper |
| --- | --- | --- | --- |
| Zoom-then-Diagnose | 70.8 | Not recorded | 6a0fe2eaf984739ed6739c13 |
| MedVLM-R1 | 55.6 | Not recorded | 6a0fe2eaf984739ed6739c13 |
| CoF | 55.2 | Not recorded | 6a0fe2eaf984739ed6739c13 |
| Qwen2.5VL† | 54.6 | Not recorded | 6a0fe2eaf984739ed6739c13 |
| Lingshu | 54.5 | Not recorded | 6a0fe2eaf984739ed6739c13 |
| Qwen2.5VL | 48.3 | Not recorded | 6a0fe2eaf984739ed6739c13 |

### Zoom-then-Diagnose

SAcc: 70.8. Result ID: 6a100314fbc373592c0882a8.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2eaf984739ed6739c13.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe2eaf984739ed6739c13.md>)

Recorded evaluation configuration: {"Stochastic rollouts":"8 rollouts, T=0.7"}. This record does not assert independent reproduction.

### MedVLM-R1

SAcc: 55.6. Result ID: 6a100314fbc373592c0882a5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2eaf984739ed6739c13.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77831e209131cea73bcd.md>)

Recorded evaluation configuration: {"Stochastic rollouts":"8 rollouts, T=0.7"}. This record does not assert independent reproduction.

### CoF

SAcc: 55.2. Result ID: 6a100314fbc373592c0882a7.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2eaf984739ed6739c13.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b91e209131cea7a0cd.md>)

Recorded evaluation configuration: {"Stochastic rollouts":"8 rollouts, T=0.7"}. This record does not assert independent reproduction.

### Qwen2.5VL†

SAcc: 54.6. Result ID: 6a100314fbc373592c0882a6.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2eaf984739ed6739c13.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Stochastic rollouts":"8 rollouts, T=0.7"}. This record does not assert independent reproduction.

### Lingshu

SAcc: 54.5. Result ID: 6a100314fbc373592c0882a4.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2eaf984739ed6739c13.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795a1e209131cea7d387.md>)

Recorded evaluation configuration: {"Stochastic rollouts":"8 rollouts, T=0.7"}. This record does not assert independent reproduction.

### Qwen2.5VL

SAcc: 48.3. Result ID: 6a100314fbc373592c0882a3.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2eaf984739ed6739c13.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Stochastic rollouts":"8 rollouts, T=0.7"}. This record does not assert independent reproduction.

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