Healthcare is more and more embracing AI to enhance workflow administration, affected person communication, and diagnostic and therapy assist. It’s important that these AI-based techniques are usually not solely high-performing, but additionally environment friendly and privacy-preserving. It’s with these concerns in thoughts that we constructed and just lately launched Well being AI Developer Foundations (HAI-DEF). HAI-DEF is a group of light-weight open fashions designed to supply builders strong beginning factors for their very own well being analysis and software growth. As a result of HAI-DEF fashions are open, builders retain full management over privateness, infrastructure and modifications to the fashions. In Might of this yr, we expanded the HAI-DEF assortment with MedGemma, a group of generative fashions primarily based on Gemma 3 which can be designed to speed up healthcare and lifesciences AI growth.
At present, we’re proud to announce two new fashions on this assortment. The primary is MedGemma 27B Multimodal, which enhances the previously-released 4B Multimodal and 27B text-only fashions by including assist for advanced multimodal and longitudinal digital well being report interpretation. The second new mannequin is MedSigLIP, a light-weight picture and textual content encoder for classification, search, and associated duties. MedSigLIP is predicated on the identical picture encoder that powers the 4B and 27B MedGemma fashions.
MedGemma and MedSigLIP are robust beginning factors for medical analysis and product growth. MedGemma is helpful for medical textual content or imaging duties that require producing free textual content, like report technology or visible query answering. MedSigLIP is advisable for imaging duties that contain structured outputs like classification or retrieval. All the above fashions could be run on a single GPU, and MedGemma 4B and MedSigLIP may even be tailored to run on cellular {hardware}.
Full particulars of MedGemma and MedSigLIP growth and analysis could be discovered within the MedGemma technical report.
