使用双重人工智能平台检测未报告的肺结节。
Use of a Dual Artificial Intelligence Platform to Detect Unreported Lung Nodules.
机构信息
From the Department of Radiology, University of California San Diego Health, San Diego, CA.
IMedis-AI Ltd, Raanana, Israel.
出版信息
J Comput Assist Tomogr. 2021;45(2):318-322. doi: 10.1097/RCT.0000000000001118.
OBJECTIVE
To investigate the performance of Dual-AI Deep Learning Platform in detecting unreported pulmonary nodules that are 6 mm or greater, comprising computer-vision (CV) algorithm to detect pulmonary nodules, with positive results filtered by natural language processing (NLP) analysis of the dictated report.
METHODS
Retrospective analysis of 5047 chest CT scans and corresponding reports. Cases which were both CV algorithm positive (nodule ≥ 6 mm) and NLP negative (nodule not reported), were outputted for review by 2 chest radiologists.
RESULTS
The CV algorithm detected nodules that are 6 mm or greater in 1830 (36.3%) of 5047 cases. Three hundred fifty-five (19.4%) were unreported by the radiologist, as per NLP algorithm. Expert review determined that 139 (39.2%) of 355 cases were true positives (2.8% of all cases). One hundred thirty (36.7%) of 355 cases were unnecessary alerts-vague language in the report confounded the NLP algorithm. Eighty-six (24.2%) of 355 cases were false positives.
CONCLUSIONS
Dual-AI platform detected actionable unreported nodules in 2.8% of chest CT scans, yet minimized intrusion to radiologist's workflow by avoiding alerts for most already-reported nodules.
目的
研究双人工智能深度学习平台在检测未报告的 6 毫米或更大的肺结节方面的性能，该平台包含用于检测肺结节的计算机视觉 (CV) 算法，并通过对报告进行自然语言处理 (NLP) 分析来过滤阳性结果。
方法
回顾性分析了 5047 例胸部 CT 扫描和相应的报告。CV 算法阳性（结节≥6 毫米）且 NLP 阴性（结节未报告）的病例，由 2 名胸部放射科医生进行审查。
结果
CV 算法在 5047 例病例中检测到了 1830 例（36.3%）直径为 6 毫米或更大的结节。根据 NLP 算法，有 355 例（19.4%）未被放射科医生报告。专家审查确定，在这 355 例中有 139 例（39.2%）为真阳性（占所有病例的 2.8%）。在这 355 例中有 130 例（36.7%）为不必要的警报——报告中的模糊语言使 NLP 算法混淆。在这 355 例中有 86 例（24.2%）为假阳性。
结论
双人工智能平台在 2.8%的胸部 CT 扫描中检测到了可操作的未报告结节，但通过避免对大多数已报告结节发出警报，最大限度地减少了对放射科医生工作流程的干扰。
Zotero 插件