Unsupervised domain adaptation (UDA) aims to learn a model trained on source domain and performs well on unlabeled target domain. In medical image segmentation field, most existing UDA methods depend on adversarial learning to address the domain gap between different image modalities, which is ineffective due to its complicated training process. In this paper, we propose a simple yet effective UDA method based on frequency and spatial domain transfer uner multi-teacher distillation framework. In the frequency domain, we first introduce non-subsampled contourlet transform for identifying domain-invariant and domain-variant frequency components (DIFs and DVFs), and then keep the DIFs unchanged while replacing the DVFs of the source domain images with that of the target domain images to narrow the domain gap. In the spatial domain, we propose a batch momentum update-based histogram matching strategy to reduce the domain-variant image style bias. Experiments on two cross-modality medical image segmentation datasets (cardiac, abdominal) show that our proposed method achieves superior performance compared to state-of-the-art methods.
翻译:无人监督的域适应(UDA) 旨在学习在源域方面受过训练的模型,并在未贴标签的目标域上表现良好。在医疗图像分割领域,大多数现有的UDA方法都依赖于对抗性学习,以解决不同图像模式之间的领域差距,由于培训过程复杂,这种差距是无效的。在本文中,我们提出了一个简单而有效的UDA方法,其基础是频率和空间域传输单体多教师蒸馏框架。在频率领域,我们首先引入了非辅助抽样的轮廓转换,以识别域变量和域变量频率组件(DIFs和DVFs),然后保持DIFs保持不变,同时用目标域图图像取代源域域图的DVFs,以缩小域间差距。在空间领域,我们提出了基于批量动力更新的直方图匹配战略,以降低域变量图像样式的偏差。在两种跨模式医学图像分割数据集(Cardiac, abdminal)上进行的实验表明,我们拟议的方法比州-Art-Art-Art-Art-Art-Art-Art-Art-s)实现了优。