[2603.22935] Ran Score: a LLM-based Evaluation Score for Radiology Report Generation

Computer Science > Artificial Intelligence arXiv:2603.22935 (cs) [Submitted on 24 Mar 2026] Title:Ran Score: a LLM-based Evaluation Score for Radiology Report Generation Authors:Ran Zhang, Yucong Lin, Zhaoli Su, Bowen Liu, Danni Ai, Tianyu Fu, Deqiang Xiao, Jingfan Fan, Yuanyuan Wang, Mingwei Gao, Yuwan Hu, Shuya Gao, Jingtao Li, Jian Yang, Hong Song, Hongliang Sun View a PDF of the paper titled Ran Score: a LLM-based Evaluation Score for Radiology Report Generation, by Ran Zhang and 15 other authors View PDF HTML (experimental) Abstract:Chest X-ray report generation and automated evaluation are limited by poor recognition of low-prevalence abnormalities and inadequate handling of clinically important language, including negation and ambiguity. We develop a clinician-guided framework combining human expertise and large language models for multi-label finding extraction from free-text chest X-ray reports and use it to define Ran Score, a finding-level metric for report evaluation. Using three non-overlapping MIMIC-CXR-EN cohorts from a public chest X-ray dataset and an independent ChestX-CN validation cohort, we optimize prompts, establish radiologist-derived reference labels and evaluate report generation models. The optimized framework improves the macro-averaged score from 0.753 to 0.956 on the MIMIC-CXR-EN development cohort, exceeds the CheXbert benchmark by 15.7 percentage points on directly comparable labels, and shows robust generalization on the ChestX-CN validatio...