Maldonado Fabien, Varghese Cyril, Rajagopalan Srinivasan, Duan Fenghai, Balar Aneri B, Lakhani Dhairya A, Antic Sanja L, Massion Pierre P, Johnson Tucker F, Karwoski Ronald A, Robb Richard A, Bartholmai Brian J, Peikert Tobias
Division of Allergy, Pulmonary and Critical Care Medicine, Vanderbilt University Medical Center, Nashville, TN, USA.
These authors contributed equally to this work.
Eur Respir J. 2021 Apr 1;57(4). doi: 10.1183/13993003.02485-2020. Print 2021 Apr.
Implementation of low-dose chest computed tomography (CT) lung cancer screening and the ever-increasing use of cross-sectional imaging are resulting in the identification of many screen- and incidentally detected indeterminate pulmonary nodules. While the management of nodules with low or high pre-test probability of malignancy is relatively straightforward, those with intermediate pre-test probability commonly require advanced imaging or biopsy. Noninvasive risk stratification tools are highly desirable.
We previously developed the BRODERS classifier (Benign aggRessive nODule Evaluation using Radiomic Stratification), a conventional predictive radiomic model based on eight imaging features capturing nodule location, shape, size, texture and surface characteristics. Herein we report its external validation using a dataset of incidentally identified lung nodules (Vanderbilt University Lung Nodule Registry) in comparison to the Brock model. Area under the curve (AUC), as well as sensitivity, specificity, negative and positive predictive values were calculated.
For the entire Vanderbilt validation set (n=170, 54% malignant), the AUC was 0.87 (95% CI 0.81-0.92) for the Brock model and 0.90 (95% CI 0.85-0.94) for the BRODERS model. Using the optimal cut-off determined by Youden's index, the sensitivity was 92.3%, the specificity was 62.0%, the positive (PPV) and negative predictive values (NPV) were 73.7% and 87.5%, respectively. For nodules with intermediate pre-test probability of malignancy, Brock score of 5-65% (n=97), the sensitivity and specificity were 94% and 46%, respectively, the PPV was 78.4% and the NPV was 79.2%.
The BRODERS radiomic predictive model performs well on an independent dataset and may facilitate the management of indeterminate pulmonary nodules.
低剂量胸部计算机断层扫描（CT）肺癌筛查的实施以及横断面成像的使用日益增加，导致发现了许多筛查和偶然发现的不确定肺结节。虽然对恶性肿瘤预测试概率低或高的结节的管理相对简单，但那些预测试概率中等的结节通常需要先进的成像或活检。非常需要非侵入性风险分层工具。
我们之前开发了BRODERS分类器（使用放射组学分层的良性侵袭性结节评估），这是一种基于八个成像特征的传统预测放射组学模型，这些特征捕获结节的位置、形状、大小、纹理和表面特征。在此，我们报告了其与Brock模型相比，使用偶然发现的肺结节数据集（范德比尔特大学肺结节登记处）进行的外部验证。计算曲线下面积（AUC）以及敏感性、特异性、阴性和阳性预测值。
对于整个范德比尔特验证集（n = 170，54%为恶性），Brock模型的AUC为0.87（95%CI 0.81 - 0.92），BRODERS模型的AUC为0.90（95%CI 0.85 - 0.94）。使用约登指数确定的最佳截断值，敏感性为92.3%，特异性为62.0%，阳性（PPV）和阴性预测值（NPV）分别为73.7%和87.5%。对于恶性肿瘤预测试概率中等的结节，Brock评分为5 - 65%（n = 97），敏感性和特异性分别为94%和46%，PPV为78.4%，NPV为79.2%。
BRODERS放射组学预测模型在独立数据集上表现良好，可能有助于不确定肺结节的管理。
