# Multimodal Medical Analysis

MedGemma is a medical-specific multimodal AI model developed by Google, based on the Gemma 3 architecture, focusing on medical text and image understanding.

MedGemma-4B-IT is a medical-focused image-to-text generation model developed by Google.

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

This is a multimodal model based on the Qwen2 architecture, focusing on text generation, image-to-text, and visual question answering tasks.

A radiology image-assisted interpretation model fine-tuned based on unsloth/Llama-3.2-11B-Vision-Instruct, with optimized runtime speed doubled

A multimodal large language model (MLLM) specifically designed for interpreting electrocardiogram (ECG) images, capable of handling various ECG-related tasks from diverse data sources.

LLaVA-Med is a large language-vision biomedical assistant trained through curriculum learning, specifically designed for biomedical visual question answering tasks.

A Chinese medical multimodal large language model based on the LLaVA-1.5 architecture, focusing on visual question answering tasks in the medical field.

This is a text generation model based on chest X-ray images, capable of generating radiology impression reports from medical imaging.

BabyDoctor is a multimodal large language model that combines the capabilities of CLiP and LLaMA 2. It can understand and generate text while also comprehending images. The model has been fine-tuned specifically for interpreting radiology images such as X-rays, ultrasounds, MRIs, and CT scans.

RCLIP is a vision-language model fine-tuned from CLIP specifically optimized for medical image analysis in the radiology domain.

A multimodal foundation model based on ViT-B/16 visual encoder and PubMedBERT text encoder trained on the Quilt-1M pathology video dataset

A CLIP ViT-B/32 vision-language foundation model trained on the Quilt-1M pathology video dataset, specifically designed for histological analysis