# Ultrasound Lesion Diagnosis and Localization on Liver Ultrasound (test) Source: [Ultrasound Lesion Diagnosis and Localization on Liver Ultrasound (test)]() Collection index: [llms.txt]() Data updated: 2026-05-22T07:17:43.019Z Evaluation of Ultrasound Lesion Diagnosis and Localization performance on the test split of the Liver Ultrasound dataset, reporting Accuracy (Acc) and mean Intersection over Union (mIoU). 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 Lesion Diagnosis and Localization | | Dataset (including any stated split) | Liver Ultrasound (test) | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [mIoU](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Zoom-then-Diagnose | 69.3 | Not recorded | 6a0fe2eaf984739ed6739c13 | | Chain-of-Focus | 56.8 | Not recorded | 6a0fe2eaf984739ed6739c13 | | MedVLM-R1 | 53.4 | Not recorded | 6a0fe2eaf984739ed6739c13 | | Lingshu | 51.1 | Not recorded | 6a0fe2eaf984739ed6739c13 | | Qwen2.5-VL† | 51.1 | Not recorded | 6a0fe2eaf984739ed6739c13 | | Qwen2.5-VL | 47.7 | Not recorded | 6a0fe2eaf984739ed6739c13 | ### Zoom-then-Diagnose Accuracy: 69.3. Result ID: 6a100314fbc373592c088296. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"multi-turn","tool-calling":true}. This record does not assert independent reproduction. ### Chain-of-Focus Accuracy: 56.8. Result ID: 6a100314fbc373592c088294. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"multi-turn","tool-calling":true}. This record does not assert independent reproduction. ### MedVLM-R1 Accuracy: 53.4. Result ID: 6a100314fbc373592c088293. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"single-turn","tool-calling":false}. This record does not assert independent reproduction. ### Lingshu Accuracy: 51.1. Result ID: 6a100314fbc373592c088292. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"single-turn","tool-calling":false}. This record does not assert independent reproduction. ### Qwen2.5-VL† Accuracy: 51.1. Result ID: 6a100314fbc373592c088295. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"multi-turn","tool-calling":true}. This record does not assert independent reproduction. ### Qwen2.5-VL Accuracy: 47.7. Result ID: 6a100314fbc373592c088291. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"single-turn","tool-calling":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.