Unsupervised Domain Adaptation for Anatomical Landmark Detection
This work addresses the practical issue of performance drop in medical imaging due to domain shifts, offering a solution for anatomical landmark detection when labeled data is unavailable in target domains, though it is incremental as it builds on existing UDA techniques.
The paper tackles the problem of domain shift in anatomical landmark detection by proposing an unsupervised domain adaptation framework that combines self-training with dynamic thresholds and domain adversarial learning, achieving significant reductions in domain gap and outperforming existing UDA methods on cephalometric and lung datasets.
Recently, anatomical landmark detection has achieved great progresses on single-domain data, which usually assumes training and test sets are from the same domain. However, such an assumption is not always true in practice, which can cause significant performance drop due to domain shift. To tackle this problem, we propose a novel framework for anatomical landmark detection under the setting of unsupervised domain adaptation (UDA), which aims to transfer the knowledge from labeled source domain to unlabeled target domain. The framework leverages self-training and domain adversarial learning to address the domain gap during adaptation. Specifically, a self-training strategy is proposed to select reliable landmark-level pseudo-labels of target domain data with dynamic thresholds, which makes the adaptation more effective. Furthermore, a domain adversarial learning module is designed to handle the unaligned data distributions of two domains by learning domain-invariant features via adversarial training. Our experiments on cephalometric and lung landmark detection show the effectiveness of the method, which reduces the domain gap by a large margin and outperforms other UDA methods consistently. The code is available at https://github.com/jhb86253817/UDA_Med_Landmark.