Kentucky Imaging Technologies, LLC., Louisville, KY, USA.
Computer Vision and Image Processing Laboratory (CVIP Lab), University of Louisville, Louisville, KY, 40292, USA.
Int J Comput Assist Radiol Surg. 2017 Oct;12(10):1809-1818. doi: 10.1007/s11548-017-1626-1. Epub 2017 Jun 16.
This article examines feature-based nodule description for the purpose of nodule classification in chest computed tomography scanning.
Three features based on (i) Gabor filter, (ii) multi-resolution local binary pattern (LBP) texture features and (iii) signed distance fused with LBP which generates a combinational shape and texture feature are utilized to provide feature descriptors of malignant and benign nodules and non-nodule regions of interest. Support vector machines (SVMs) and k-nearest neighbor (kNN) classifiers in serial and two-tier cascade frameworks are optimized and analyzed for optimal classification results of nodules.
A total of 1191 nodule and non-nodule samples from the Lung Image Data Consortium database is used for analysis. Classification using SVM and kNN classifiers is examined. The classification results from the two-tier cascade SVM using Gabor features showed overall better results for identifying non-nodules, malignant and benign nodules with average area under the receiver operating characteristics (AUC-ROC) curves of 0.99 and average f1-score of 0.975 over the two tiers.
In the results, higher overall AUCs and f1-scores were obtained for the non-nodules cases using any of the three features, showing the greatest distinguishability over nodules (benign/malignant). SVM and kNN classifiers were used for benign, malignant and non-nodule classification, where Gabor proved to be the most effective of the features for classification. The cascaded framework showed the greatest distinguishability between benign and malignant nodules.
本文研究了基于特征的结节描述，旨在对胸部 CT 扫描中的结节进行分类。
利用基于（i）Gabor 滤波器、（ii）多分辨率局部二值模式（LBP）纹理特征和（iii）与 LBP 融合的符号距离的三种特征，生成组合形状和纹理特征，为恶性和良性结节以及非结节感兴趣区域提供特征描述符。支持向量机（SVM）和 K-最近邻（kNN）分类器在串行和两级级联框架中进行优化和分析，以获得最佳的结节分类结果。
使用 Lung Image Data Consortium 数据库中的 1191 个结节和非结节样本进行分析。检查了 SVM 和 kNN 分类器的分类。使用 Gabor 特征的两级级联 SVM 的分类结果表明，在识别非结节、恶性和良性结节方面总体效果更好，在两级的平均接收者操作特征（AUC-ROC）曲线下面积（AUC-ROC）分别为 0.99 和平均 f1 分数为 0.975。
在结果中，使用任何三种特征对非结节病例获得了更高的整体 AUC 和 f1 分数，与结节（良性/恶性）相比表现出最大的可区分性。SVM 和 kNN 分类器用于良性、恶性和非结节分类，其中 Gabor 被证明是分类最有效的特征。级联框架在良性和恶性结节之间表现出最大的可区分性。
