Reconfigurable Radiology Labels Without Relabeling
For researchers and practitioners using chest X-ray datasets, this work reduces the cost and effort of adapting label schemas to new tasks or sites, though it is an incremental improvement over existing label extraction methods.
The authors present a pipeline that converts free-text radiology reports into multi-label matrices, enabling label schema reconfiguration via dictionary edits without relabeling. Reconfiguring MIMIC-CXR takes 196 seconds (vs. $6.6K for relabeling), and 43% of studies have findings outside CheXpert-14, with image probes reaching 0.78 AUROC on long-tail labels.
Public chest-radiograph (CXR) datasets are typically released with small, fixed label schemas such as CheXpert-14. However, the underlying free-text reports describe far more findings -- and which findings matter depends on the task, site, and reader. We release a pipeline that converts free-text reports into multi-label matrices and then reconfigures the label schema through dictionary edits rather than new inference passes, i.e., without relabeling the corpus. After this one-time pass, reconfiguring MIMIC-CXR (223K reports) from cached annotations takes 196 seconds with no API cost, compared to \$6.6K for an equivalent relabeling pass with Claude Opus 4.7. Using a 58-label taxonomy, we show that 43\% of CXR studies contain at least one finding outside CheXpert-14. Image probes trained on these labels match CheXpert-14 probes on shared targets while also reaching 0.78 AUROC on expert-reviewed long-tail labels that CheXpert-14 cannot represent. These results suggest a different unit of work for radiology labeling: once reports are structured, the label schema becomes a configuration to edit, not a corpus to relabel.