# Medical Multimodal

MedGemma is a series of medical-specialized AI models optimized based on Gemma 3, with the 27B version focusing on medical text comprehension and reasoning tasks

MedGemma is a medical-specific multimodal model based on Gemma 3, excelling in medical text and image understanding, supporting analysis of various medical images including chest X-rays, dermatology, ophthalmology, etc.

MedGemma is a medical multimodal model optimized based on Gemma 3, specifically designed for medical text and image understanding, available in 4B and 27B versions.

ConceptCLIP is a large-scale vision-language pre-training model enhanced with medical concepts, suitable for various medical imaging modalities, capable of achieving robust performance across multiple medical imaging tasks.