Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China.
Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Chongqing, 400038, P. R. China.
Nat Commun. 2024 Feb 14;15(1):1347. doi: 10.1038/s41467-024-45599-z.
Accurate identification and localization of multiple abnormalities are crucial steps in the interpretation of chest X-rays (CXRs); however, the lack of a large CXR dataset with bounding boxes severely constrains accurate localization research based on deep learning. We created a large CXR dataset named CXR-AL14, containing 165,988 CXRs and 253,844 bounding boxes. On the basis of this dataset, a deep-learning-based framework was developed to identify and localize 14 common abnormalities and calculate the cardiothoracic ratio (CTR) simultaneously. The mean average precision values obtained by the model for 14 abnormalities reached 0.572-0.631 with an intersection-over-union threshold of 0.5, and the intraclass correlation coefficient of the CTR algorithm exceeded 0.95 on the held-out, multicentre and prospective test datasets. This framework shows an excellent performance, good generalization ability and strong clinical applicability, which is superior to senior radiologists and suitable for routine clinical settings.
准确识别和定位多种异常是解读胸部 X 光片（CXR）的关键步骤；然而，缺乏带有边界框的大型 CXR 数据集严重限制了基于深度学习的准确定位研究。我们创建了一个名为 CXR-AL14 的大型 CXR 数据集，其中包含 165988 张 CXR 和 253844 个边界框。在此数据集的基础上，开发了一种基于深度学习的框架，用于同时识别和定位 14 种常见异常，并计算心胸比（CTR）。该模型对 14 种异常的平均精度均值达到 0.572-0.631，交并比阈值为 0.5，在保留、多中心和前瞻性测试数据集上，CTR 算法的组内相关系数超过 0.95。该框架表现出优异的性能、良好的泛化能力和强大的临床适用性，优于高级放射科医生，适用于常规临床环境。
