Automated Detection of Measurements and Their Descriptors in Radiology Reports Using a Hybrid Natural Language Processing Algorithm
Automated Detection of Measurements and Their Descriptors in Radiology Reports Using a Hybrid Natural Language Processing Algorithm
复制标题
DOI：
10.1007/s10278-019-00237-9
复制
发表时间：
2019-08-01
影响因子：
4.4
通讯作者：
Rubin, Daniel L.
中科院分区：
文献类型：
--
作者：
Bozkurt, Selen;Alkim, Emel;Rubin, Daniel L.
放射学测量报告在自由文本报告，它是具有挑战性的治疗计划，如病变总结和癌症反应评估提取这样的措施。这项工作的目的是开发和评估自然语言处理（NLP）管道，该管道可以提取测量值及其核心描述符，例如时间性，解剖实体，成像观察，RadLex描述符，序列号，图像编号和各种放射学报告（MR，CT和乳房X线照片）中的片段。我们创建了一个混合NLP管道，该管道集成了基于规则的特征提取模块和条件随机场（CRF）模型，用于从放射学报告中提取测量值，并将它们与临床相关特征（如解剖实体或成像观察结果）联系起来。该管道在1117份CT/MR报告上进行了训练，并在一组独立的100份专家注释的CT/MR报告上评估了系统的性能，并在25份乳房X线摄影报告上进行了测试。系统在CT/MR报告中检测到806个测量值中的813个; 784个为真阳性，29个为假阳性，0个为假阴性。同样，从乳房X线摄影报告中，96%的测量值及其修改器被正确提取。我们的方法可以使计算机化的应用程序，可以利用总结病变测量不同形式的放射学报告，并通过跟踪相同的病变沿着多个放射学遭遇改善实践的发展。
Radiological measurements are reported in free text reports, and it is challenging to extract such measures for treatment planning such as lesion summarization and cancer response assessment. The purpose of this work is to develop and evaluate a natural language processing (NLP) pipeline that can extract measurements and their core descriptors, such as temporality, anatomical entity, imaging observation, RadLex descriptors, series number, image number, and segment from a wide variety of radiology reports (MR, CT, and mammogram). We created a hybrid NLP pipeline that integrates rule-based feature extraction modules and conditional random field (CRF) model for extraction of the measurements from the radiology reports and links them with clinically relevant features such as anatomical entities or imaging observations. The pipeline was trained on 1117 CT/MR reports, and performance of the system was evaluated on an independent set of 100 expert-annotated CT/MR reports and also tested on 25 mammography reports. The system detected 813 out of 806 measurements in the CT/MR reports; 784 were true positives, 29 were false positives, and 0 were false negatives. Similarly, from the mammography reports, 96% of the measurements with their modifiers were extracted correctly. Our approach could enable the development of computerized applications that can utilize summarized lesion measurements from radiology report of varying modalities and improve practice by tracking the same lesions along multiple radiologic encounters.