Radiological Image Traits Predictive of Cancer Status in Pulmonary Nodules.
Radiological Image Traits Predictive of Cancer Status in Pulmonary Nodules.
复制标题
DOI：
10.1158/1078-0432.ccr-15-3102
复制
发表时间：
2017-03-15
期刊：
影响因子：
--
通讯作者：
Gillies RJ
中科院分区：
文献类型：
--
作者：
Liu Y;Balagurunathan Y;Atwater T;Antic S;Li Q;Walker RC;Smith GT;Massion PP;Schabath MB;Gillies RJ
我们提出了一种系统的方法来量化偶然识别的肺结节的基础上观察到的放射学特征（语义）量化的点尺度和机器学习方法使用这些数据来预测癌症状态。我们调查了172名低剂量计算机断层扫描（LDCT）图像的患者，其中102名和70名患者分别分组为训练和验证队列。在图像上，对24个放射学特征进行了系统评分，并建立了一个线性分类器，将这些特征与恶性状态联系起来。该模型是在有和没有尺寸描述符的情况下形成的，以消除由于结节尺寸引起的偏倚。在训练集上形成的多变量对在独立验证数据集上进行测试以评估其性能。包括尺寸测量的最佳四个特征集（集1）是短轴、轮廓、纹理和纹理，其具有0.88的受试者操作特征曲线下面积（AUROC）（准确度= 81%，灵敏度= 76.2%，特异性= 91.7%）。如果排除尺寸测量，四个最佳特征（第2组）是：位置、裂隙附着、分叶和毛刺，其预测原发性结节恶性的AUROC为0.83（准确性= 73.2%，灵敏度= 73.8%，特异性= 81.7%）。第1组和第2组的验证测试AUROC分别为0.8（准确度= 74.3%，灵敏度= 66.7%，特异性= 75.6%）和0.74（准确度= 71.4%，灵敏度= 61.9%，特异性= 75.5%）。影像学特征对预测肺结节的恶性程度有帮助。这些语义特征可以与基于大小的措施结合使用，以提高预测准确性并减少误报。
We propose a systematic methodology to quantify incidentally identified pulmonary nodules based on observed radiological traits (semantics) quantified on a point scale and a machine learning method using these data to predict cancer status. We investigated 172 patients who had low-dose computed tomography (LDCT) images, with 102 and 70 patients grouped into training and validation cohorts, respectively. On the images, 24 radiological traits were systematically scored and a linear classifier was built to relate the traits to malignant status. The model was formed both with and without size descriptors to remove bias due to nodule size. The multivariate pairs formed on the training set was tested on an independent validation data set to evaluate its performance. The best four feature set that included a size measurement (Set 1), was short axis, contour, concavity, and texture, which had an area under the receiver operator characteristic curve (AUROC) of 0.88 (Accuracy= 81%, Sensitivity= 76.2%, Specificity= 91.7%). If size measures were excluded, the four best features (Set 2) were: location, fissure attachment, lobulation, and spiculation which had an AUROC of 0.83 (Accuracy= 73.2%, Sensitivity= 73.8%, Specificity= 81.7%) in predicting malignancy in primary nodules. The validation test AUROC was 0.8 (Accuracy=74.3%, Sensitivity =66.7%, Specificity= 75.6%) and 0.74 (Accuracy=71.4%, Sensitivity = 61.9%, Specificity = 75.5%) for Sets 1 and 2, respectively. Radiological image traits are useful in predicting malignancy in lung nodules. These semantic traits can be used in combination with size-based measures to enhance prediction accuracy and reducing false positives.