Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, People's Republic of China.
Phys Med Biol. 2019 Sep 4;64(17):175012. doi: 10.1088/1361-6560/ab326a.
To predict lung nodule malignancy with a high sensitivity and specificity for low dose CT (LDCT) lung cancer screening, we propose a fusion algorithm that combines handcrafted features (HF) into the features learned at the output layer of a 3D deep convolutional neural network (CNN). First, we extracted twenty-nine HF, including nine intensity features, eight geometric features, and twelve texture features based on grey-level co-occurrence matrix (GLCM). We then trained 3D CNNs modified from three 2D CNN architectures (AlexNet, VGG-16 Net and Multi-crop Net) to extract the CNN features learned at the output layer. For each 3D CNN, the CNN features combined with the 29 HF were used as the input for the support vector machine (SVM) coupled with the sequential forward feature selection (SFS) method to select the optimal feature subset and construct the classifiers. The fusion algorithm takes full advantage of the HF and the highest level CNN features learned at the output layer. It can overcome the disadvantage of the HF that may not fully reflect the unique characteristics of a particular lesion by combining the intrinsic CNN features. Meanwhile, it also alleviates the requirement of a large scale annotated dataset for the CNNs based on the complementary of HF. The patient cohort includes 431 malignant nodules and 795 benign nodules extracted from the LIDC/IDRI database. For each investigated CNN architecture, the proposed fusion algorithm achieved the highest AUC, accuracy, sensitivity, and specificity scores among all competitive classification models.
为了在低剂量 CT（LDCT）肺癌筛查中实现对肺结节恶性肿瘤的高灵敏度和特异性预测，我们提出了一种融合算法，该算法将手工制作的特征（HF）合并到三维深度卷积神经网络（CNN）输出层学习到的特征中。首先，我们提取了 29 个 HF，包括 9 个强度特征、8 个几何特征和 12 个纹理特征，这些特征是基于灰度共生矩阵（GLCM）提取的。然后，我们对三种二维 CNN 架构（AlexNet、VGG-16 Net 和多裁剪 Net）进行了修改，以提取输出层学习到的 CNN 特征，训练了三个 3D CNN。对于每个 3D CNN，将 CNN 特征与 29 个 HF 相结合作为支持向量机（SVM）的输入，同时结合序贯前向特征选择（SFS）方法选择最佳特征子集并构建分类器。融合算法充分利用了 HF 和输出层学习到的最高水平的 CNN 特征。它可以克服 HF 的缺点，HF 可能无法完全反映特定病变的独特特征，通过与内在的 CNN 特征相结合。同时，它还减轻了 HF 对 CNN 的大规模注释数据集的要求，HF 对 CNN 起到了互补作用。患者队列包括从 LIDC/IDRI 数据库中提取的 431 个恶性结节和 795 个良性结节。对于每个被调查的 CNN 架构，所提出的融合算法在所有竞争分类模型中实现了最高的 AUC、准确性、灵敏度和特异性评分。
