Back

A Clinically-Informed Framework for Evaluating Vision-Language Models in Radiology Report Generation: Taxonomy of Errors and Risk-Aware Metric

Guan, H.; Hou, P. C.; Hong, P.; Wang, L.; Zhang, W.; Du, X.; Zhou, Z.; Zhou, L.

2025-07-14 health informatics
10.1101/2025.07.13.25331222 medRxiv
Show abstract

Recent advances in vision-language models (VLMs) have enabled automatic radiology report generation, yet current evaluation methods remain limited to general-purpose NLP metrics or coarse classification-based clinical scores. In this study, we propose a clinically informed evaluation framework for VLM-generated radiology reports that goes beyond traditional performance measures. We define a taxonomy of 12 radiology-specific error types, each annotated with clinical risk levels (low, medium, high) in collaboration with physicians. Using this framework, we conduct a comprehensive error analysis of three representative VLMs, i.e., DeepSeek VL2, CXR-LLaVA, and CheXagent, on 685 gold-standard, expert-annotated MIMIC-CXR cases. We further introduce a risk-aware evaluation metric, the Clinical Risk-weighted Error Score for Text-generation (CREST), to quantify safety impact. Our findings reveal critical model vulnerabilities, common error patterns, and condition-specific risk profiles, offering actionable insights for model development and deployment. This work establishes a safety-centric foundation for evaluating and improving medical report generation models. The source code of our evaluation framework, including CREST computation and error taxonomy analysis, is available at https://github.com/guanharry/VLM-CREST.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.