Unsupervised domain selective graph convolutional network for preoperative prediction of lymph node metastasis in gastric cancer
Unsupervised domain selective graph convolutional network for preoperative prediction of lymph node metastasis in gastric cancer
复制标题
DOI：
10.1016/j.media.2022.102467
复制
发表时间：
2022-04
影响因子：
10.9
通讯作者：
Yongtao Zhang;Ning Yuan;Zhiguo Zhang;Jie Du;Tianfu Wang;Bing Liu;A. Yang;Kuan Lv;
中科院分区：
文献类型：
--
作者：
Yongtao Zhang;Ning Yuan;Zhiguo Zhang;Jie Du;Tianfu Wang;Bing Liu;A. Yang;Kuan Lv;
基于计算机断层扫描（CT）扫描的术前淋巴结（LN）转移预测是胃癌的一项重要任务，但很少有人提出基于机器学习的技术。虽然多中心数据集增加了样本量和表示能力，但它们存在中心间异质性。为了解决上述问题，我们提出了一种新的多源域自适应框架，该框架不仅考虑了域不变和特定于域的特征，而且还实现了跨域的不平衡知识转移和类感知特征对齐。首先，我们开发了一个三维改进的特征金字塔网络（即，3D IFPN）来从高分辨率3D CT图像中提取共同的多级特征，其中特征动态转移（FDT）模块可以提升网络识别小目标（即，LN）。然后，我们设计了一个无监督域选择图卷积网络（即，UDS-GCN），它主要包括三种类型的组件：领域特定的特征提取器，领域选择器和类感知的GCN分类器。具体地，采用多个域特定特征提取器来从由3D IFPN生成的公共多级特征中学习域特定特征。通过最优传输（OT）理论设计了一个域选择器，用于控制从源域到目标域的知识转移量。一个类感知的GCN分类器的开发显式地增强/削弱跨域的所有样本对的类内/类间相似性。为了优化UDS-GCN，域选择器和类感知GCN分类器通过协作学习在迭代过程中相互提供可靠的目标伪标签。在从四个医疗中心收集的内部CT图像数据集上进行了广泛的实验，以证明我们所提出的方法的有效性。实验结果表明，该方法提高了淋巴结转移的诊断性能，优于现有的方法。我们的代码可在https://github.com/infinite-tao/LN_MSDA上免费获得。
Preoperative prediction of lymph node (LN) metastasis based on computed tomography (CT) scans is an important task in gastric cancer, but few machine learning-based techniques have been proposed. While multi-center datasets increase sample size and representation ability, they suffer from inter-center heterogeneity. To tackle the above issue, we propose a novel multi-source domain adaptation framework for this diagnosis task, which not only considers domain-invariant and domain-specific features, but also achieves the imbalanced knowledge transfer and class-aware feature alignment across domains. First, we develop a3D improved feature pyramidal network(i.e., 3D IFPN) to extract common multi-level features from the high-resolution 3D CT images, where a feature dynamic transfer (FDT) module can promote the network's ability to recognize the small target (i.e., LN). Then, we design anunsupervised domain selective graph convolutional network(i.e., UDS-GCN), which mainly includes three types of components: domain-specific feature extractor, domain selector and class-aware GCN classifier. Specifically, multiple domain-specific feature extractors are employed for learning domain-specific features from the common multi-level features generated by the 3D IFPN. A domain selector via the optimal transport (OT) theory is designed for controlling the amount of knowledge transferred from source domains to the target domain. A class-aware GCN classifier is developed to explicitly enhance/weaken the intra-class/inter-class similarity of all sample pairs across domains. To optimize UDS-GCN, the domain selector and the class-aware GCN classifier provide reliable target pseudo-labels to each other in the iterative process by collaborative learning. The extensive experiments are conducted on an in-house CT image dataset collected from four medical centers to demonstrate the efficacy of our proposed method. Experimental results verify that the proposed method boosts LN metastasis diagnosis performance and outperforms state-of-the-art methods. Our code is publically available at https://github.com/infinite-tao/LN_MSDA.