基于蒸馏LLM的全CMR报告不确定性感知结构化数据提取
Uncertainty-Aware Structured Data Extraction from Full CMR Reports via Distilled LLMs
AI总结：
本文提出CMR-EXTR框架，通过蒸馏LLM将自由文本CMR报告转为结构化数据并提供字段置信度，实现无监督推理和不确定性整合，达到99.65%的变量级准确率。
摘要：
将自由文本心脏磁共振（CMR）报告转换为可审计的结构化数据仍是队列构建、纵向整理和临床决策支持的瓶颈。我们提出CMR-EXTR，一个轻量框架，将自由文本CMR报告转换为结构化数据并为每个字段分配置信度以进行质量控制。教师-学生蒸馏管道使完全离线推理成为可能，同时限制手动标注。不确定性整合了三个互补原则--分布可信度、采样稳定性、跨字段一致性--以优先处理人工审查。实验显示，CMR-EXTR在变量级达到99.65%的准确率，证明了可靠提取和信息丰富的置信度评分。据我们所知，这是首个集成置信度估计的特定CMR提取系统。代码可在https://github.com/yuyi1005/CMR-EXTR获取。
英文摘要：
Converting free-text cardiac magnetic resonance (CMR) reports into auditable structured data remains a bottleneck for cohort assembly, longitudinal curation, and clinical decision support. We present CMR-EXTR, a lightweight framework that converts free-text CMR reports into structured data and assigns per-field confidence for quality control. A teacher-student distillation pipeline enables fully offline inference while limiting manual annotation. Uncertainty integrates three complementary principles -- distribution plausibility, sampling stability, and cross-field consistency -- to triage human review. Experiments show that CMR-EXTR achieves 99.65% variable-level accuracy, demonstrating both reliable extraction and informative confidence scores. To our knowledge, this is the first CMR-specific extraction system with integrated confidence estimation. The code is available at https://github.com/yuyi1005/CMR-EXTR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
