无需重新标注的可重构放射学标签
Reconfigurable Radiology Labels Without Relabeling
浏览论文内容
中文总结 AI 辅助
研究针对公共胸部X光数据集标签模式固定的问题，提出将自由文本报告转换为多标签矩阵，通过字典编辑重新配置标签模式的方法，无需重新标注。实验显示该方法高效且新标签探针效果好，表明放射学标签工作单元可改变。
中文摘要 AI 辅助
公共胸部X光数据集通常附带小的固定标签模式，如CheXpert - 14。但自由文本报告包含更多发现，且重要发现取决于任务、地点和读者。我们发布了一个管道，将自由文本报告转换为多标签矩阵，通过字典编辑重新配置标签模式，无需重新标注语料库。以58标签分类法显示，43%的CXR研究包含CheXpert - 14之外的至少一个发现。基于这些标签训练的图像探针在共享目标上与CheXpert - 14探针匹配，在专家评审的长尾标签上达到0.78 AUROC。结果表明放射学标签工作单元不同，报告结构化后，标签模式是可编辑的配置而非需重新标注的语料库。
英文摘要
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.
发表机构
- HOPPR
机构由 AI 辅助整理，请以论文原文为准。
