Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2505.17779 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915811548987392 |
|---|---|
| author | Le, Anjie Liu, Henan Wang, Yue Liu, Zhenyu Zhu, Rongkun Weng, Taohan Yu, Jinze Wang, Boyang Wu, Yalun Yan, Kaiwen Sun, Quanlin Jiang, Meirui Pei, Jialun Liu, Siya Zheng, Haoyun Li, Zhoujun Noble, Alison Souquet, Jacques Guo, Xiaoqing Lin, Manxi Guo, Hongcheng |
| author_facet | Le, Anjie Liu, Henan Wang, Yue Liu, Zhenyu Zhu, Rongkun Weng, Taohan Yu, Jinze Wang, Boyang Wu, Yalun Yan, Kaiwen Sun, Quanlin Jiang, Meirui Pei, Jialun Liu, Siya Zheng, Haoyun Li, Zhoujun Noble, Alison Souquet, Jacques Guo, Xiaoqing Lin, Manxi Guo, Hongcheng |
| contents | Ultrasound is a widely-used imaging modality critical to global healthcare, yet its interpretation remains challenging due to its varying image quality on operators, noises, and anatomical structures. Although large vision-language models (LVLMs) have demonstrated impressive multimodal capabilities across natural and medical domains, their performance on ultrasound remains largely unexplored. We introduce U2-BENCH, the first comprehensive benchmark to evaluate LVLMs on ultrasound understanding across classification, detection, regression, and text generation tasks. U2-BENCH aggregates 7,241 cases spanning 15 anatomical regions and defines 8 clinically inspired tasks, such as diagnosis, view recognition, lesion localization, clinical value estimation, and report generation, across 50 ultrasound application scenarios. We evaluate 23 state-of-the-art LVLMs, both open- and closed-source, general-purpose and medical-specific. Our results reveal strong performance on image-level classification, but persistent challenges in spatial reasoning and clinical language generation. U2-BENCH establishes a rigorous and unified testbed to assess and accelerate LVLM research in the uniquely multimodal domain of medical ultrasound imaging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17779 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding Le, Anjie Liu, Henan Wang, Yue Liu, Zhenyu Zhu, Rongkun Weng, Taohan Yu, Jinze Wang, Boyang Wu, Yalun Yan, Kaiwen Sun, Quanlin Jiang, Meirui Pei, Jialun Liu, Siya Zheng, Haoyun Li, Zhoujun Noble, Alison Souquet, Jacques Guo, Xiaoqing Lin, Manxi Guo, Hongcheng Computer Vision and Pattern Recognition Machine Learning Ultrasound is a widely-used imaging modality critical to global healthcare, yet its interpretation remains challenging due to its varying image quality on operators, noises, and anatomical structures. Although large vision-language models (LVLMs) have demonstrated impressive multimodal capabilities across natural and medical domains, their performance on ultrasound remains largely unexplored. We introduce U2-BENCH, the first comprehensive benchmark to evaluate LVLMs on ultrasound understanding across classification, detection, regression, and text generation tasks. U2-BENCH aggregates 7,241 cases spanning 15 anatomical regions and defines 8 clinically inspired tasks, such as diagnosis, view recognition, lesion localization, clinical value estimation, and report generation, across 50 ultrasound application scenarios. We evaluate 23 state-of-the-art LVLMs, both open- and closed-source, general-purpose and medical-specific. Our results reveal strong performance on image-level classification, but persistent challenges in spatial reasoning and clinical language generation. U2-BENCH establishes a rigorous and unified testbed to assess and accelerate LVLM research in the uniquely multimodal domain of medical ultrasound imaging. |
| title | U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2505.17779 |