Google has launched an update of MedGemma, its open-source AI model for medical imaging interpretation and clinical speech-to-text processing.
MedGemma 1.5 4B is now capable of analyzing 3D CTs and MRI scans, as well as histopathology slides, the company said, in a January 13 blog post announcing the update. Other new capabilities include the following:
Longitudinal medical imaging: Chest x-ray time series review
Anatomical localization: Localization of anatomical features in chest x-rays
Medical document understanding: Extracting structured data from medical lab reports
MedGemma 1.5 4B also improves accuracy on core capabilities for text, medical records, and 2D images over MedGemma 1 4B, the company said.
“We are publishing the updated 4B model size today to provide an ideal compute-efficient starting point for developers that is small enough to run offline, and developers can continue to use our MedGemma 1 27B parameter model for more complex text-based applications,” Google said.
In addition, the company launched MedASR, a new open-source automated speech recognition model that has been fine-tuned for medical dictation. The initial release of MedASR enables developers to convert medical speech to text and pairs with MedGemma for advanced reasoning tasks, the company said.
Both MedGemma 1.5 and MedASR are free for research and commercial use and can be downloaded from Hugging Face or trained and adapted into scalable applications in the cloud on Vertex AI, Google noted.
