CXR-Retrieve: Compositional Text-to-Image Retrieval in Chest Radiography

arXiv:2607.27779v1 Announce Type: new Abstract: Large chest radiography archives are difficult to search because most studies are paired only with free-text reports rather than structured clinical annotations. Vision-language models offer a natural interface for text-to-image retrieval, but current biomedical models are primarily optimized for report-to-image matching rather than for satisfying short clinical search queries. This creates an objective mismatch: a model may retrieve images related...