Saved in:
Bibliographic Details
Main Authors: Zhang, Ran, Lin, Yucong, Su, Zhaoli, Liu, Bowen, Ai, Danni, Fu, Tianyu, Xiao, Deqiang, Fan, Jingfan, Wang, Yuanyuan, Gao, Mingwei, Hu, Yuwan, Gao, Shuya, Li, Jingtao, Yang, Jian, Song, Hong, Sun, Hongliang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.22935
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918406260785152
author Zhang, Ran
Lin, Yucong
Su, Zhaoli
Liu, Bowen
Ai, Danni
Fu, Tianyu
Xiao, Deqiang
Fan, Jingfan
Wang, Yuanyuan
Gao, Mingwei
Hu, Yuwan
Gao, Shuya
Li, Jingtao
Yang, Jian
Song, Hong
Sun, Hongliang
author_facet Zhang, Ran
Lin, Yucong
Su, Zhaoli
Liu, Bowen
Ai, Danni
Fu, Tianyu
Xiao, Deqiang
Fan, Jingfan
Wang, Yuanyuan
Gao, Mingwei
Hu, Yuwan
Gao, Shuya
Li, Jingtao
Yang, Jian
Song, Hong
Sun, Hongliang
contents 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 validation cohort. Here we show that clinician-guided prompt optimization improves agreement with a radiologist-derived reference standard and that Ran Score enables finding-level evaluation of report fidelity, particularly for low-prevalence abnormalities.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22935
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Ran Score: a LLM-based Evaluation Score for Radiology Report Generation
Zhang, Ran
Lin, Yucong
Su, Zhaoli
Liu, Bowen
Ai, Danni
Fu, Tianyu
Xiao, Deqiang
Fan, Jingfan
Wang, Yuanyuan
Gao, Mingwei
Hu, Yuwan
Gao, Shuya
Li, Jingtao
Yang, Jian
Song, Hong
Sun, Hongliang
Artificial Intelligence
Human-Computer Interaction
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 validation cohort. Here we show that clinician-guided prompt optimization improves agreement with a radiologist-derived reference standard and that Ran Score enables finding-level evaluation of report fidelity, particularly for low-prevalence abnormalities.
title Ran Score: a LLM-based Evaluation Score for Radiology Report Generation
topic Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2603.22935