ASTAR: Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora

Researchers introduced ASTAR, an LLM-based framework that automatically generates standardized radiology reporting templates from large-scale clinical free-text corpora, reducing template development from weeks to hours. In experiments on 4,215 fetal brain MRI reports from multiple centers, the ASTAR-induced template outperformed two expert-curated templates in coverage, information fidelity, diagnostic fidelity, and expert-rated usability. The code is available at https://github.com/birthlab/ASTAR.

arXiv:2608.20369v1 Announce Type: new Abstract: Structured reporting converts free-text radiology narratives into queryable data keys, facilitating cohort assembly, longitudinal tracking, and training label generation for medical AI. The prevailing paradigm follows a two-stage pipeline: 1 constructing a reporting template, 2 extracting information to populate it. While the extraction stage has benefited from advances in large language models LLMs , template construction remains a manual bottleneck relying on labor-intensive expert consensus that is static, difficult to scale, and may fail to capture real-world reporting diversity. We address this limitation with \textbf{\texttt{ASTAR}}, an LLM-based framework for Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora. Extensive experiments on 4,215 fetal brain MRI reports from multiple centers demonstrate that the \textbf{\texttt{ASTAR}}-induced template surpasses two expert-curated templates across template coverage, information fidelity, diagnostic fidelity, and expert-rated usability, reducing template development from weeks of committee deliberation to hours of automated processing. Code: https://github.com/birthlab/ASTAR