{"id":708,"date":"2025-09-07T08:35:15","date_gmt":"2025-09-07T08:35:15","guid":{"rendered":"https:\/\/harrison.ai\/?page_id=708"},"modified":"2025-11-27T20:02:24","modified_gmt":"2025-11-27T09:02:24","slug":"radiology-foundation-model","status":"publish","type":"page","link":"https:\/\/harrison.ai\/radiology-foundation-model\/","title":{"rendered":"Harrison.rad.1"},"content":{"rendered":"
\n
\n
\n
\n
\n
\n <\/span>\n <\/span>\n <\/span>\n <\/span>\n <\/span>\n <\/div>\n
\n \n <\/span>\n <\/span>\n <\/span>\n \n <\/span>\n <\/span>\n <\/span>\n \n <\/span>\n <\/span>\n <\/span>\n <\/div>\n <\/div>\n
\"\"<\/div> <\/div>\n
\n Harrison.rad.1<\/span>

Introducing Harrison.rad.1, the latest frontier in radiology-specific foundational models.<\/h1>
\n Access now. <\/span><\/a>\n <\/div>\n \n <\/div>\n <\/div>\n <\/div>\n <\/section>\n\n\n\n\n
<\/div>\n\n\n\n\n
\n
\n
\n <\/span>\n <\/span>\n <\/span>\n <\/div>\n

With increasing challenges from rising imaging volumes, workforce shortages and growing complexity of medical images, specialised capabilities from foundation models have the potential to accelerate development of tools to scale global healthcare.
\r\n
\r\nHarrison.rad.1 is a specialised multimodal LLM for radiology, it is not a medical device but rather an enabling technology that could support innovation across the radiology workflow. Launched in 2024, we are actively exploring its applications and welcome collaboration with partners to research this emerging field.<\/h2> \n <\/div>\n <\/section>\n\n\n\n
\n
\n
\n
\"\"<\/div>\n
\n \n <\/div>\n
\n
\n

Announcement:
The latest frontier in radiology-specific foundational models is now publicly available for research use.\u00a0<\/h2>
\n Access now <\/span><\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n\n <\/div>\n <\/section>\n\n\n\n
\n
\n\n
\n

Harrison.rad.1 outperforms other frontier models by ~2x in the FRCR 2B Rapids exam.<\/h2>
\n \"\" <\/div>\n
\n
\n

Harrison.rad.1 excels in the same radiology exams taken by human radiologists, as well as in benchmarks against other foundational models.<\/p>\n

The Fellowship of the Royal College of Radiologists (FRCR) 2B Rapids exam is considered one of the leading and toughest certifications for radiologists. Only 40-59% of human radiologists pass on their first attempt. Radiologists who re-attempt the exam within a year of passing score an average of 50.88 out of 60 (84.8%)*.<\/p>\n

Harrison.rad.1 scored 51.4 out of 60 (85.67%). Other competing models, including OpenAI\u2019s GPT-4o, Microsoft\u2019s LLaVA-Med, Anthropic\u2019s Claude 3.5 Sonnet and Google\u2019s Gemini 1.5 Pro, mostly scored below 30**, which is statistically no better than random guessing.***<\/p>\n<\/div>\n <\/div>\n Learn more <\/span><\/a>\n

\n

*British Medical Journal<\/a><\/p>\n

**Data on file
\n***As measured by mock examinations, actual FRCR 2B Rapids questions are not publicly available<\/p>\n <\/div>\n

FRCR Diagnostic Score<\/h2>< \"\" <\/div>\n\n <\/div>\n <\/section>\n\n\n\n
\n
\n

Accelerating validation and responsible introduction of generative AI in healthcare.<\/h2><\/div>
\n \n \n \n \n <\/g>\n <\/svg>\n
\n \"\" <\/div>\n