Liu Xiaofeng, Yoo Chaehwa, Xing Fangxu, Kuo C-C Jay, El Fakhri Georges, Kang Je-Won, Woo Jonghye
Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA, United States.
Department of Electronic and Electrical Engineering and Graduate Program in Smart Factory, Ewha Womans University, Seoul, South Korea.
Front Neurosci. 2022 Jun 2;16:837646. doi: 10.3389/fnins.2022.837646. eCollection 2022.
Unsupervised domain adaptation (UDA) is an emerging technique that enables the transfer of domain knowledge learned from a labeled source domain to unlabeled target domains, providing a way of coping with the difficulty of labeling in new domains. The majority of prior work has relied on both source and target domain data for adaptation. However, because of privacy concerns about potential leaks in sensitive information contained in patient data, it is often challenging to share the data and labels in the source domain and trained model parameters in cross-center collaborations. To address this issue, we propose a practical framework for UDA with a black-box segmentation model trained in the source domain only, without relying on source data or a white-box source model in which the network parameters are accessible. In particular, we propose a knowledge distillation scheme to gradually learn target-specific representations. Additionally, we regularize the confidence of the labels in the target domain via unsupervised entropy minimization, leading to performance gain over UDA without entropy minimization. We extensively validated our framework on a few datasets and deep learning backbones, demonstrating the potential for our framework to be applied in challenging yet realistic clinical settings.
无监督域适应（UDA）是一种新兴技术，它能够将从有标签的源域学到的域知识转移到无标签的目标域，提供了一种应对新域中标签标注困难的方法。大多数先前的工作都依赖源域和目标域数据进行适应。然而，由于担心患者数据中包含的敏感信息可能泄露，在跨中心合作中共享源域中的数据和标签以及训练好的模型参数往往具有挑战性。为了解决这个问题，我们提出了一个实用的UDA框架，该框架使用仅在源域中训练的黑盒分割模型，而不依赖源数据或网络参数可访问的白盒源模型。具体来说，我们提出了一种知识蒸馏方案来逐步学习特定于目标的表示。此外，我们通过无监督熵最小化来规范目标域中标签的置信度，从而比没有熵最小化的UDA获得性能提升。我们在几个数据集和深度学习骨干网络上广泛验证了我们的框架，证明了我们的框架在具有挑战性但现实的临床环境中应用的潜力。
