Lunguage: A Benchmark for Structured and Sequential Chest X-ray Interpretation

TL;DR

LUNGUAGE is a new benchmark dataset and evaluation framework for structured, longitudinal chest X-ray report generation, capturing disease progression over time with expert annotations and a novel scoring metric.

Contribution

Introduces the first benchmark, structuring framework, and evaluation metric for sequential radiology report generation and assessment.

Findings

LUNGUAGESCORE effectively evaluates structured report quality.

The benchmark supports both single-report and longitudinal assessments.

Empirical results show the scoring metric aligns well with expert judgments.

Abstract

Radiology reports convey detailed clinical observations and capture diagnostic reasoning that evolves over time. However, existing evaluation methods are limited to single-report settings and rely on coarse metrics that fail to capture fine-grained clinical semantics and temporal dependencies. We introduce LUNGUAGE, a benchmark dataset for structured radiology report generation that supports both single-report evaluation and longitudinal patient-level assessment across multiple studies. It contains 1,473 annotated chest X-ray reports, each reviewed by experts, and 186 of them contain longitudinal annotations to capture disease progression and inter-study intervals, also reviewed by experts. Using this benchmark, we develop a two-stage structuring framework that transforms generated reports into fine-grained, schema-aligned structured reports, enabling longitudinal interpretation. We also propose LUNGUAGESCORE, an interpretable metric that compares structured outputs at the entity, relation, and attribute level while modeling temporal consistency across patient timelines. These contributions establish the first benchmark dataset, structuring framework, and evaluation metric for sequential radiology reporting, with empirical results demonstrating that LUNGUAGESCORE effectively supports structured report evaluation. The code is available at: https://github.com/SuperSupermoon/Lunguage