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

TL;DR

This paper introduces Ran Score, a new evaluation metric for radiology report generation that leverages large language models and clinician input to better recognize abnormalities and handle clinical language nuances.

Contribution

It presents a clinician-guided framework for multi-label finding extraction and introduces Ran Score, a finding-level metric that improves evaluation accuracy over existing benchmarks.

Findings

Ran Score significantly outperforms previous benchmarks.

Framework generalizes well across different cohorts.

Prompt optimization enhances agreement with radiologist standards.

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 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.