首个中英双语胸部X光定位报告数据集，支持精准医学影像理解。
PadChest-GR: A Bilingual Chest X-ray Dataset for Grounded Radiology Report Generation
- 基于PadChest构建，含4555例带定位标注的胸片
- 每例含7037条阳性+3422条阴性发现描述，支持细粒度定位
- 适合研究医学图像生成与跨语言报告建模的团队使用
放射科报告生成（RRG）旨在从临床影像生成自由文本报告。接地式放射科报告生成（GRRG）通过在图像上定位具体发现来扩展RRG。目前尚无用于训练GRRG模型的手动标注胸部X光（CXR）数据集。本文提出一个名为PadChest-GR（接地报告）的数据集，源自PadChest，专为训练胸部X光的GRRG模型而设计。我们构建了一个公开的双语数据集，包含4,555例胸片研究，其中3,099例存在异常，1,456例正常，每例均包含英文和西班牙文的完整发现句子列表，描述所有存在的（阳性）和不存在的（阴性）发现。总计包含7,037条阳性发现句和3,422条阴性发现句。每条阳性发现句关联最多两组由不同医生标注的边界框，并附有发现类型、位置及进展的类别标签。据我们所知，PadChest-GR是首个专门用于训练胸部X光图像理解与报告生成模型的手动标注数据集。通过包含详细的定位信息和所有临床相关发现的全面标注，该数据集为开发和评估基于胸部X光的GRRG模型提供了宝贵资源。数据集可通过 https://bimcv.cipf.es/bimcv-projects/padchest-gr/ 申请下载。
原文摘要 · Abstract (English)
Radiology report generation (RRG) aims to create free-text radiology reports from clinical imaging. Grounded radiology report generation (GRRG) extends RRG by including the localisation of individual findings on the image. Currently, there are no manually annotated chest X-ray (CXR) datasets to train GRRG models. In this work, we present a dataset called PadChest-GR (Grounded-Reporting) derived from PadChest aimed at training GRRG models for CXR images. We curate a public bi-lingual dataset of 4,555 CXR studies with grounded reports (3,099 abnormal and 1,456 normal), each containing complete lists of sentences describing individual present (positive) and absent (negative) findings in English and Spanish. In total, PadChest-GR contains 7,037 positive and 3,422 negative finding sentences. Every positive finding sentence is associated with up to two independent sets of bounding boxes labelled by different readers and has categorical labels for finding type, locations, and progression. To the best of our knowledge, PadChest-GR is the first manually curated dataset designed to train GRRG models for understanding and interpreting radiological images and generated text. By including detailed localization and comprehensive annotations of all clinically relevant findings, it provides a valuable resource for developing and evaluating GRRG models from CXR images. PadChest-GR can be downloaded under request from https://bimcv.cipf.es/bimcv-projects/padchest-gr/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。