RadGraph-XL: A Large-Scale Expert-Annotated Dataset for Entity and Relation Extraction from Radiology Reports

Radiology reports are essential for clinical care but pose challenges for
automated processing due to their unstructured nature. Existing datasets like
RadGraph-1.0 focus narrowly on chest X-rays (CXR), limiting their
applicability. We introduce RadGraph-XL, a large-scale, expert-annotated
dataset of 2,300 radiology reports with over 410,000 labeled entities and
relations, spanning four anatomy-modality pairs: chest computed tomography
(CT), abdomen/pelvis CT, brain magnetic resonance imaging (MR), and CXR.

Each report is annotated by board-certified radiologists using a detailed
schema that captures observations, anatomical references, and their
relationships. A novel post-processing step identifies measurement-related
entities, a clinically valuable category. Trained models using RadGraph-XL
outperform prior methods and GPT-4, and generalize well to out-of-domain data
such as deep vein thrombosis (DVT) ultrasound reports.

RadGraph-XL is released publicly with models and annotations to support
applications in clinical natural language processing (NLP), medical imaging
artificial intelligence, and foundation model evaluation, setting a new
benchmark for structured information extraction in radiology.

放射学报告是临床诊疗不可或缺的核心资料，但因其非结构化的天然属性，给自动化处理带来了诸多挑战。现有诸如RadGraph-1.0的数据集仅聚焦于胸部X射线（Chest X-rays, CXR），极大限制了其应用范围。
我们推出了RadGraph-XL，这是一个大规模、经专家标注的数据集，包含2300份放射学报告，共计超过41万个标注实体与关系，涵盖四大解剖-模态组合：胸部计算机断层扫描（Computed Tomography, CT）、腹部/盆腔CT、脑部磁共振成像（Magnetic Resonance Imaging, MR）以及胸部X射线（Chest X-rays, CXR）。
每份报告均由经执业认证的放射科医师基于详细标注框架完成标注，该框架可捕获观测结果、解剖学参照对象及其相互关系。我们新增了一项创新性后处理步骤，用于识别与测量相关的实体——这是一类具有重要临床价值的实体类别。
基于RadGraph-XL训练的模型性能优于此前的各类方法与GPT-4，且可良好泛化至域外数据，例如深静脉血栓形成（Deep Vein Thrombosis, DVT）超声报告。
RadGraph-XL已与配套模型及标注文件公开发布，旨在支撑临床自然语言处理（Natural Language Processing, NLP）、医学影像人工智能以及基础模型评估领域的相关应用，为放射学领域的结构化信息抽取任务树立了全新基准。