Prototype-Based Knowledge Guidance for Fine-Grained Structured Radiology Reporting

ArXi:2603.11938v1 Announce Type: new Structured radiology reporting promises faster, consistent communication than free text, but automation remains difficult as models must make many fine-grained, discrete decisions about rare findings and attributes from limited structured supervision. In contrast, free-text reports are produced at scale in routine care and implicitly encode fine-grained, image-linked information through detailed descriptions. To leverage this unstructured knowledge, we propose ProtoSR, an approach for injecting free-text information into structured report population.