论文标题
使用特征分离和GCN进行医学图像分类，无监督的域适应
Unsupervised Domain Adaptation Using Feature Disentanglement And GCNs For Medical Image Classification
论文作者
论文摘要
深度学习的成功为许多医学图像分析任务树立了新的基准。但是，在训练（源）数据和测试（目标）数据之间存在分布变化的情况下，深层模型通常无法概括。一种通常用于反向分配变化的方法是域的适应性：使用目标域中的样本来学习分布的转移。在这项工作中，我们提出了一种无监督的域自适应方法，该方法使用图形神经网络以及解开的语义和域不变结构特征，从而可以在分布偏移之间更好地性能。我们提出了交换自动编码器的扩展名，以获得更具歧视性的功能。我们测试了两个具有分配变化的具有挑战性的医学图像数据集上的分类方法 - 多中心胸部X射线图像和组织病理学图像。实验表明，与其他域适应方法相比，我们的方法可实现最新的结果。
The success of deep learning has set new benchmarks for many medical image analysis tasks. However, deep models often fail to generalize in the presence of distribution shifts between training (source) data and test (target) data. One method commonly employed to counter distribution shifts is domain adaptation: using samples from the target domain to learn to account for shifted distributions. In this work we propose an unsupervised domain adaptation approach that uses graph neural networks and, disentangled semantic and domain invariant structural features, allowing for better performance across distribution shifts. We propose an extension to swapped autoencoders to obtain more discriminative features. We test the proposed method for classification on two challenging medical image datasets with distribution shifts - multi center chest Xray images and histopathology images. Experiments show our method achieves state-of-the-art results compared to other domain adaptation methods.
