Google announced the launch of MedGemma, which the company says contains the most capable open models that help developers build healthcare-based AI applications to examine medical images, generate medical image reports, triage patients or answer questions about medical images.
The open models, which users can fine-tune, come in two variants: a 4B multimodal version and a 27B text-only version.
The tech giant says the multimodal version can be used as a starting point for apps classifying medical images in radiology, digital pathology, skin images and fundus.
The models can also be used for apps aimed at generating medical reports and answering questions about images.
The text-only version can be a launching point for applications that require medical knowledge, such as those aimed at interviewing patients, triaging, summarization and for clinical decision support.
Google said in a statement that the text-only version, which is larger than the multimodal version, will generally produce the best performance for most use cases.
“MedGemma is a developer model that requires validation on the developer’s intended use case. Based on those validation results, the user will likely need to further adapt the model to improve performance. Below are some types of adaptation developers can use to improve MedGemma’s performance for their use cases,” Google said in a statement.
“MedGemma can be fine-tuned for improved performance on the existing tasks it’s been trained on, or to add additional tasks to its repertoire.”
THE LARGER TREND
The implementation of AI into medical imaging has transformed healthcare, according to a survey published by MDPI’s journal Bioengineering (Basel).
“AI-based diagnostic tools not only speed up the interpretation of complex images but also improve early detection of disease, ultimately delivering better outcomes for patients. Additionally, AI-based image processing facilitates personalized treatment plans, thereby optimizing healthcare delivery,” the survey’s authors wrote.
“By combining cutting-edge AI techniques and their practical applications, it is clear that AI will continue shaping the future of healthcare in profound and positive ways.”
Digital health companies currently using AI for medical imaging analysis include imaging and care coordination company Viz.ai, AI-enabled imaging company Aidoc, and Lunit, a provider of AI-powered solutions for cancer diagnostics and therapeutics.
Another company is Med-tech outfit iCAD, which announced in 2022 that it would incorporate Google Health’s mammography AI technology into its breast-imaging tools thanks to a strategic development and commercialization agreement.
Credit: Source link
