Foundation Models in Biomedical Imaging: Turning Hype into Reality

ArXi:2512.15808v2 Announce Type: replace-cross Foundation models (FMs) are driving a prominent shift in biomedical imaging from task-specific models to unified backbone models for diverse tasks. This opens an avenue to integrate imaging, pathology, clinical records, and genomics data into a composite system. However, this vision contrasts sharply with modern medicine's trajectory toward granular sub-specialization. This tension, coupled with data scarcity, domain heterogeneity, and limited interpretability, creates a gap between benchmark success and real-world clinical value.