Department of Radiology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China; Department of Cancer Imaging and Metabolism, H. Lee Moffitt Cancer Center, Tampa, FL.
Department of Cancer Imaging and Metabolism, H. Lee Moffitt Cancer Center, Tampa, FL.
Clin Lung Cancer. 2018 Mar;19(2):148-156.e3. doi: 10.1016/j.cllc.2017.10.002. Epub 2017 Oct 13.
Lung computed tomography (CT) Screening Reporting and Data System (lung-RADS) has standardized follow-up and management decisions in lung cancer screening. To date, little is known how lung-RADS classification compares with radiological semantic features in risk prediction and diagnostic discrimination.
To compare the performance of radiological semantic features and lung-RADS in predicting nodule malignancy in lung cancer screening.
We used data and low-dose CT (LDCT) images from the National Lung Screening Trial (NLST). The training cohort contained 60 patients with screen-detected incident lung cancers who had a positive baseline screen (T0) that was not diagnosed and then was diagnosed at second follow-up (T2), and 139 nodule-positive controls who had 3 consecutive positive screens (T0 to T2) that were not diagnosed as lung cancer. The testing cohort included 40 patients with incident lung cancers that were diagnosed at first follow-up (T1) and 40 nodule-positive controls. Twenty-four semantic features were scored on a point scale from the LDCT images. Multivariable linear predictor model was built on the semantic features and the performances were compared with lung-RADS in 3 screening rounds. We also combined non-size-based semantic features with lung-RADS to improve malignancy detection.
At T0, the average area under the receiver operating characteristic curve (AUROC) for border definition in risk prediction was 0.72. The average AUROC for contour at T1 in risk prediction and T2 in diagnostic discrimination was 0.82 and 0.88, respectively. By comparison, the average AUROC of lung-RADS at T0, T1 and T2 were 0.60, 0.76 and 0.87, respectively. The combined model of the semantic features and lung-RADS shows improvement with AUROCs of 0.74, 0.88 and 0.96 at T0, T1, and T2, respectively, achieved by adding border definition (at T0) or contour (at T1 and T2).
We find semantic features defined by border definition and contour performed similar to lung-RADS at follow-up time point and outperformed lung-RADS at baseline. These semantics alongside of lung-RADS shows improved performance to detect malignancy.
肺癌计算机断层扫描（CT）筛查报告和数据系统（lung-RADS）已经使肺癌筛查的随访和管理决策标准化。迄今为止，尚不清楚 lung-RADS 分类在风险预测和诊断鉴别方面与放射学语义特征相比如何。
比较放射学语义特征和 lung-RADS 在预测肺癌筛查中结节恶性程度方面的性能。
我们使用了国家肺癌筛查试验（NLST）的数据和低剂量 CT（LDCT）图像。训练队列包含 60 名在基线筛查（T0）中发现的肺癌筛查患者，这些患者的筛查结果呈阳性，但未确诊，然后在第二次随访（T2）中确诊，还有 139 名结节阳性对照者，他们连续 3 次筛查（T0 到 T2）结果均未被诊断为肺癌。测试队列包括 40 名在首次随访（T1）中确诊的肺癌患者和 40 名结节阳性对照者。在 LDCT 图像上对 24 个语义特征进行评分。在语义特征上建立多变量线性预测模型，并在 3 个筛查轮次中比较其与 lung-RADS 的性能。我们还结合了非基于大小的语义特征与 lung-RADS，以提高恶性肿瘤的检出率。
在 T0 时，用于预测风险的边界定义的受试者工作特征曲线下面积（AUROC）平均值为 0.72。用于预测 T1 时的轮廓和用于诊断鉴别 T2 时的轮廓的平均 AUROC 分别为 0.82 和 0.88。相比之下，lung-RADS 在 T0、T1 和 T2 的平均 AUROC 分别为 0.60、0.76 和 0.87。语义特征与 lung-RADS 的组合模型在 T0、T1 和 T2 时的 AUROC 分别为 0.74、0.88 和 0.96，通过添加边界定义（在 T0）或轮廓（在 T1 和 T2）可实现改进。
我们发现边界定义和轮廓定义的语义特征在随访时间点与 lung-RADS 表现相似，在基线时优于 lung-RADS。这些语义特征与 lung-RADS 一起可以提高恶性肿瘤的检出率。
