Annalise.ai parent company Harrison.ai has launched Harrison.rad.1, a radiology-specific vision language model.
Harrison.rad.1 is dialogue-based and can perform open-ended chats related to x-ray images, detect and localize radiological findings, generate reports, and provide longitudinal reasoning based on clinical history and patient context, Harrison.ai said.
In testing, Harrison.rad.1 performed on par with experienced radiologists on the Fellowship of the Royal College of Radiologists (FRCR) 2B Rapids exam and outperformed other models such as OpenAI's GPT-4o, Anthropic's Claude-3.5-sonnet, Google's Gemini-1.5 Pro, and Microsoft's LLaVA-Med, according to the company.
The model is now being made accessible to selected industry partners, healthcare professionals, and regulators around the world, the company added.
