UNISOUND unveils “U2-RadiMed”, China’s first full-chain multi-modal medical imaging large model

Bulletin Express08-13

UNISOUND AI Technology Co., Ltd. announced the commercial roll-out of its proprietary medical imaging multi-modal large model, U2-RadiMed. The platform integrates image interpretation, report generation, clinical reasoning, decision-making, and visual question answering in a single solution, supporting mixed inputs of chest X-rays, CT and MRI images together with text.

U2-RadiMed forms a six-pillar capability suite—report generation, lesion detection and localization, clinical reasoning, clinical decision-making, general medical visual Q&A, and advanced medical reasoning—enabling a complete workflow from image review to conclusion. In independent benchmarks, the model achieved an overall score of 55.47, topping competitors such as Gemini 3.1 and GPT-5.4. It also ranked first in four specialist sub-categories, posting a 37.58 score in lesion detection and localization, and led the MedBench 5.0 full-modality evaluation with 57.20.

On the application front, U2-RadiMed addresses traditional AI limitations in single-image analysis by handling multi-temporal image comparisons, disease-progression tracking, differential diagnosis, and automated report drafting. Deployed on UNISOUND’s MaaS platform “Token Hub”, the model offers multi-image input and a 40K-token context window, facilitating rapid integration into radiology and clinical workflows across medical institutions.

Management underscored that the launch extends UNISOUND’s product stack—from a general foundational LLM to the tri-medical professional LLM and now the dedicated medical imaging model—reinforcing the company’s leadership in medical AI. Ongoing efforts will focus on broadening large-model applications across healthcare to enhance clinical efficiency and create long-term value for shareholders.

Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.

Comments

We need your insight to fill this gap
Leave a comment