Department of Radiology, Huzhou Central Hospital, Affiliated Central Hospital of Huzhou University, 1558 Sanhuan North Road, Huzhou, Zhejiang, 313000, People's Republic of China.
Department of Radiology, Fudan University Shanghai Cancer Center, 270 Dongan Road, Shanghai, 200032, People's Republic of China.
Phys Med Biol. 2021 Mar 4;66(6):065015. doi: 10.1088/1361-6560/abe735.
OBJECTIVES: This study aims to develop a computer-aided diagnosis (CADx) scheme to classify between benign and malignant ground glass nodules (GGNs), and fuse deep leaning and radiomics imaging features to improve the classification performance. METHODS: We first retrospectively collected 513 surgery histopathology confirmed GGNs from two centers. Among these GGNs, 100 were benign and 413 were malignant. All malignant tumors were stage I lung adenocarcinoma. To segment GGNs, we applied a deep convolutional neural network and residual architecture to train and build a 3D U-Net. Then, based on the pre-trained U-Net, we used a transfer learning approach to build a deep neural network (DNN) to classify between benign and malignant GGNs. With the GGN segmentation results generated by 3D U-Net, we also developed a CT radiomics model by adopting a series of image processing techniques, i.e. radiomics feature extraction, feature selection, synthetic minority over-sampling technique, and support vector machine classifier training/testing, etc. Finally, we applied an information fusion method to fuse the prediction scores generated by DNN based CADx model and CT-radiomics based model. To evaluate the proposed model performance, we conducted a comparison experiment by testing on an independent testing dataset. RESULTS: Comparing with DNN model and radiomics model, our fusion model yielded a significant higher area under a receiver operating characteristic curve (AUC) value of 0.73 ± 0.06 (P < 0.01). The fusion model generated an accuracy of 75.6%, F1 score of 84.6%, weighted average F1 score of 70.3%, and Matthews correlation coefficient of 43.6%, which were higher than the DNN model and radiomics model individually. CONCLUSIONS: Our experimental results demonstrated that (1) applying a CADx scheme was feasible to diagnosis of early-stage lung adenocarcinoma, (2) deep image features and radiomics features provided complementary information in classifying benign and malignant GGNs, and (3) it was an effective way to build DNN model with limited dataset by using transfer learning. Thus, to build a robust image analysis based CADx model, one can combine different types of image features to decode the imaging phenotypes of GGN.
目的：本研究旨在开发一种计算机辅助诊断（CADx）方案，以对良恶性磨玻璃结节（GGN）进行分类，并融合深度学习和放射组学成像特征以提高分类性能。
方法：我们首先从两个中心回顾性地收集了 513 例经手术病理证实的 GGN，其中 100 例为良性，413 例为恶性。所有恶性肿瘤均为 I 期肺腺癌。为了分割 GGN，我们应用了深度卷积神经网络和残差架构来训练和构建 3D U-Net。然后，基于预训练的 U-Net，我们使用迁移学习方法构建了一个深度神经网络（DNN），以对良恶性 GGN 进行分类。利用 3D U-Net 生成的 GGN 分割结果，我们还通过采用一系列图像处理技术，即放射组学特征提取、特征选择、合成少数过采样技术和支持向量机分类器训练/测试等，开发了一个 CT 放射组学模型。最后，我们应用信息融合方法融合由 DNN 基于 CADx 模型和 CT 放射组学模型生成的预测得分。为了评估所提出模型的性能，我们在一个独立的测试数据集上进行了对比实验。
结果：与 DNN 模型和放射组学模型相比，我们的融合模型在受试者工作特征曲线（AUC）下的面积值（0.73±0.06）显著更高（P<0.01）。融合模型生成了 75.6%的准确率、84.6%的 F1 分数、70.3%的加权平均 F1 分数和 43.6%的马修斯相关系数，均高于 DNN 模型和放射组学模型。
结论：我们的实验结果表明：（1）应用 CADx 方案诊断早期肺腺癌是可行的；（2）深度学习图像特征和放射组学特征在对良恶性 GGN 进行分类时提供了互补信息；（3）通过迁移学习使用有限的数据集来构建 DNN 模型是一种有效的方法。因此，为了构建稳健的基于图像分析的 CADx 模型，可以结合不同类型的图像特征来解码 GGN 的成像表型。
Front Oncol. 2024-9-6
Zotero 插件