We're proud to release an approach for AI generation of radiology reports in medical imaging that enables controlling the sensitivity and specificity of the output reports. This is a critical function for safety and regulatory compliance. Importantly the method is plug-and-play,
RadFusion: Confidence-based control of clinical report generation
arxiv.org/abs/2608.10505
AI-generated radiology report generation has focused on creating a single, best report. But clinical settings have different costs for misses vs. false alarms. Thus, we may want different
Our team within Microsoft Health and Life Sciences is happy to announce the release of MedImageInsight, an open-source medical imaging embedding model. (1/n)