This paper introduces a novel, entity-aware metric, termed as Radiological
Report (Text) Evaluation (RaTEScore), to assess the quality of medical reports
generated by AI models. RaTEScore emphasizes crucial medical entities such as
diagnostic outcomes and anatomical details, and is robust against complex
medical synonyms and sensitive to negation expressions. Technically, we
developed a comprehensive medical NER dataset, RaTE-NER, and trained an NER
model specifically for this purpose. This model enables the decomposition of
complex radiological reports into constituent medical entities. The metric
itself is derived by comparing the similarity of entity embeddings, obtained
from a language model, based on their types and relevance to clinical
significance. Our evaluations demonstrate that RaTEScore aligns more closely
with human preference than existing metrics, validated both on established
public benchmarks and our newly proposed RaTE-Eval benchmark.

该研究介绍了一种名为 Radiological Report Evaluation (RaTEScore) 的新型、面向实体的度量标准，用于评估由人工智能模型生成的医学报告的质量。RaTEScore 强调诊断结果和解剖细节等重要医学实体，并且对于复杂的医学近义词和否定表达式具有鲁棒性。该度量标准通过比较从语言模型中获得的实体嵌入的相似性，根据其类型和与临床重要性的相关性来衡量。我们的评估结果显示，RaTEScore 与人类偏好更加一致，这一点在现有的公开基准和我们新提出的 RaTE-Eval 基准上得到了验证。