Voice-controlled super-resolution ultrasound imaging and reporting powered by multimodal large language models
Ning Guo, Zixuan Deng, Qin Tan, Kai Sheng, Xuyang Wang, Shiyun Wang, Chen Hua · 2026
Read Voice-controlled super-resolution ultrasound imaging and reporting powered by multimodal large language models by Ning Guo, Zixuan Deng, Qin Tan, Kai Sheng, Xuyang Wang, Shiyun Wang, Chen Hua (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13645727.txt.
Description
Ning Guo and six colleagues describe, in a 2026 paper, an ultrasound system that doctors can run by voice with help from large language models. Super-resolution ultrasound can show tiny blood vessels beyond normal imaging limits, yet its settings are complex and reporting is slow. The team's platform pairs custom imaging hardware with two AI models, one for language and one for image reading. Spoken commands are turned into imaging settings automatically.
The system then rebuilds the sharp images, measures vessel features, and drafts structured reports in about four minutes. Fourteen clinicians judged the reports well formed and consistent in wording. A built-in score adjusts filtering of the microbubbles used for contrast. The authors say the setup could bring this demanding imaging method closer to everyday hospital use in brain, cancer, and heart care.
Catalog record
| CREATOR | Ning Guo, Zixuan Deng, Qin Tan, Kai Sheng, Xuyang Wang, Shiyun Wang, Chen Hua |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 106010 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |