Liu Kai, Li Qiong, Ma Jiechao, Zhou Zijian, Sun Mengmeng, Deng Yufeng, Tu Wenting, Wang Yun, Fan Li, Xia Chen, Xiao Yi, Zhang Rongguo, Liu Shiyuan
Department of Radiology, Changzheng Hospital, Second Military Medical University, 415 Fengyang Rd, Shanghai, China 20003 (K.L., Q.L., W.T., Y.W., L.F., Y.X., S.L.); and Infervision Advanced Institute, Beijing, China (J.M., Z.Z., M.S., Y.D., C.X., R.Z.).
Radiol Artif Intell. 2019 May 29;1(3):e180084. doi: 10.1148/ryai.2019180084. eCollection 2019 May.
To compare sensitivity in the detection of lung nodules between the deep learning (DL) model and radiologists using various patient population and scanning parameters and to assess whether the radiologists' detection performance could be enhanced when using the DL model for assistance.
A total of 12 754 thin-section chest CT scans from January 2012 to June 2017 were retrospectively collected for DL model training, validation, and testing. Pulmonary nodules from these scans were categorized into four types: solid, subsolid, calcified, and pleural. The testing dataset was divided into three cohorts based on radiation dose, patient age, and CT manufacturer. Detection performance of the DL model was analyzed by using a free-response receiver operating characteristic curve. Sensitivities of the DL model and radiologists were compared by using exploratory data analysis. False-positive detection rates of the DL model were compared within each cohort. Detection performance of the same radiologist with and without the DL model were compared by using nodule-level sensitivity and patient-level localization receiver operating characteristic curves.
The DL model showed elevated overall sensitivity compared with manual review of pulmonary nodules. No significant dependence regarding radiation dose, patient age range, or CT manufacturer was observed. The sensitivity of the junior radiologist was significantly dependent on patient age. When radiologists used the DL model for assistance, their performance improved and reading time was reduced.
DL shows promise to enhance the identification of pulmonary nodules and benefit nodule management.© RSNA, 2019
比较深度学习（DL）模型与放射科医生在使用不同患者群体和扫描参数时检测肺结节的敏感性，并评估在使用DL模型辅助时放射科医生的检测性能是否能够提高。
回顾性收集2012年1月至2017年6月期间的12754例胸部薄层CT扫描图像用于DL模型的训练、验证和测试。这些扫描图像中的肺结节分为四种类型：实性、亚实性、钙化性和胸膜性。测试数据集根据辐射剂量、患者年龄和CT制造商分为三个队列。使用自由响应式接收器操作特性曲线分析DL模型的检测性能。通过探索性数据分析比较DL模型和放射科医生的敏感性。在每个队列中比较DL模型的假阳性检测率。使用结节水平敏感性和患者水平定位接收器操作特性曲线比较同一名放射科医生在有和没有DL模型辅助时的检测性能。
与人工阅片相比，DL模型显示出更高的总体敏感性。未观察到辐射剂量、患者年龄范围或CT制造商之间存在显著相关性。初级放射科医生的敏感性显著依赖于患者年龄。当放射科医生使用DL模型辅助时，他们的表现有所改善，阅读时间减少。
DL有望提高肺结节的识别能力并有益于结节管理。©RSNA，2019
