Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China.
Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, 510515, China.
Int J Comput Assist Radiol Surg. 2022 Jul;17(7):1303-1311. doi: 10.1007/s11548-022-02587-2. Epub 2022 Mar 15.
Computed tomography (CT) images can display internal organs of patients and are particularly suitable for preoperative surgical diagnoses. The increasing demands for computer-aided systems in recent years have facilitated the development of many automated algorithms, especially deep convolutional neural networks, to segment organs and tumors or identify diseases from CT images. However, performances of some systems are highly affected by the amount of training data, while the sizes of medical image data sets, especially three-dimensional (3D) data sets, are usually small. This condition limits the application of deep learning.
In this study, given a practical clinical data set that has 3D CT images of 20 patients with renal carcinoma, we designed a pipeline employing transfer learning to alleviate the detrimental effect of the small sample size. A dual-channel fine segmentation network (FS-Net) was constructed to segment kidney and tumor regions, with 210 publicly available 3D images from a competition employed during the training phase. We also built discriminative classifiers to classify the benign and malignant tumors based on the segmented regions, where both handcrafted and deep features were tested.
Our experimental results showed that the Dice values of segmented kidney and tumor regions were 0.9662 and 0.7685, respectively, which were better than those of state-of-the-art methods. The classification model using radiomics features can classify most of the tumors correctly.
The designed FS-Net was demonstrated to be more effective than simply fine-tuning on the practical small size data set given that the model can borrow knowledge from large auxiliary data without diluting the signal in primary data. For the small data set, radiomics features outperformed deep features in the classification of benign and malignant tumors. This work highlights the importance of architecture design in transfer learning, and the proposed pipeline is anticipated to provide a reference and inspiration for small data analysis.
计算机断层扫描（CT）图像可以显示患者的内部器官，特别适用于术前手术诊断。近年来，对计算机辅助系统的需求不断增加，这促进了许多自动化算法的发展，特别是深度卷积神经网络，以从 CT 图像中分割器官和肿瘤或识别疾病。然而，一些系统的性能受到训练数据量的极大影响，而医学图像数据集的大小，特别是三维（3D）数据集，通常较小。这种情况限制了深度学习的应用。
在这项研究中，针对一个实际的临床数据集，该数据集包含 20 例肾细胞癌患者的 3D CT 图像，我们设计了一个采用迁移学习的流水线来减轻小样本量的不利影响。构建了双通道精细分割网络（FS-Net）来分割肾脏和肿瘤区域，在训练阶段使用了 210 个来自比赛的公开可用的 3D 图像。我们还构建了判别分类器，根据分割区域对良性和恶性肿瘤进行分类，测试了手工和深度特征。
我们的实验结果表明，分割的肾脏和肿瘤区域的 Dice 值分别为 0.9662 和 0.7685，优于最新方法。使用放射组学特征的分类模型可以正确分类大多数肿瘤。
与简单地对实际小数据集进行微调相比，所设计的 FS-Net 被证明更为有效，因为模型可以从大型辅助数据中借用知识，而不会稀释原始数据中的信号。对于小数据集，在良性和恶性肿瘤的分类中，放射组学特征优于深度特征。这项工作强调了迁移学习中架构设计的重要性，所提出的流水线有望为小数据分析提供参考和启示。
