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.
@article{arxiv.2605.08045,
title = {Uncertainty-Aware Structured Data Extraction from Full CMR Reports via Distilled LLMs},
author = {Yi Yu and Parker Martin and Zhenyu Bu and Yixuan Liu and Yi-Yu Zheng and Orlando Simonetti and Yuchi Han and Yuan Xue},
journal= {arXiv preprint arXiv:2605.08045},
year = {2026}
}