University of Maryland, Baltimore County, MD, USA.
J Digit Imaging. 2021 Jun;34(3):647-666. doi: 10.1007/s10278-020-00417-y. Epub 2021 Feb 2.
We present a hybrid algorithm to estimate lung nodule malignancy that combines imaging biomarkers from Radiologist's annotation with image classification of CT scans. Our algorithm employs a 3D Convolutional Neural Network (CNN) as well as a Random Forest in order to combine CT imagery with biomarker annotation and volumetric radiomic features. We analyze and compare the performance of the algorithm using only imagery, only biomarkers, combined imagery + biomarkers, combined imagery + volumetric radiomic features, and finally the combination of imagery + biomarkers + volumetric features in order to classify the suspicion level of nodule malignancy. The National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) IDRI dataset is used to train and evaluate the classification task. We show that the incorporation of semi-supervised learning by means of K-Nearest-Neighbors (KNN) can increase the available training sample size of the LIDC-IDRI, thereby further improving the accuracy of malignancy estimation of most of the models tested although there is no significant improvement with the use of KNN semi-supervised learning if image classification with CNNs and volumetric features is combined with descriptive biomarkers. Unexpectedly, we also show that a model using image biomarkers alone is more accurate than one that combines biomarkers with volumetric radiomics, 3D CNNs, and semi-supervised learning. We discuss the possibility that this result may be influenced by cognitive bias in LIDC-IDRI because malignancy estimates were recorded by the same radiologist panel as biomarkers, as well as future work to incorporate pathology information over a subset of study participants.
我们提出了一种混合算法来估计肺结节的恶性程度，该算法结合了放射科医生注释的成像生物标志物与 CT 扫描的图像分类。我们的算法采用了 3D 卷积神经网络（CNN）和随机森林，以便将 CT 图像与生物标志物注释和体积放射组学特征相结合。我们仅使用图像、仅使用生物标志物、结合图像+生物标志物、结合图像+体积放射组学特征以及最终结合图像+生物标志物+体积特征来分析和比较算法的性能，以分类结节恶性程度的可疑程度。国家癌症研究所（NCI）肺部图像数据库联盟（LIDC）IDRI 数据集用于训练和评估分类任务。我们表明，通过 K-最近邻（KNN）实现的半监督学习可以增加 LIDC-IDRI 的可用训练样本量，从而进一步提高大多数测试模型的恶性估计准确性，尽管如果将 CNN 图像分类与体积特征结合起来，使用 KNN 半监督学习并不能显著提高准确性与描述性生物标志物。出乎意料的是，我们还表明，仅使用图像生物标志物的模型比结合生物标志物与体积放射组学、3D CNN 和半监督学习的模型更准确。我们讨论了这种结果可能受到 LIDC-IDRI 中认知偏差影响的可能性，因为恶性估计是由与生物标志物相同的放射科医生小组记录的，以及未来在研究参与者的子集中纳入病理学信息的工作。
