Semi-supervised Anatomical Landmark Detection via Shape-regulated Self-training
This work addresses the challenge of costly medical image annotation for clinicians and researchers, offering a flexible, plug-and-play solution that enhances landmark detection performance in semi-supervised settings.
The paper tackles the problem of anatomical landmark detection in medical images with limited labeled data by proposing a shape-regulated self-training framework that incorporates global shape constraints to improve pseudo-label consistency. The method outperforms other semi-supervised approaches on three datasets, achieving notable improvements in accuracy.
Well-annotated medical images are costly and sometimes even impossible to acquire, hindering landmark detection accuracy to some extent. Semi-supervised learning alleviates the reliance on large-scale annotated data by exploiting the unlabeled data to understand the population structure of anatomical landmarks. The global shape constraint is the inherent property of anatomical landmarks that provides valuable guidance for more consistent pseudo labelling of the unlabeled data, which is ignored in the previously semi-supervised methods. In this paper, we propose a model-agnostic shape-regulated self-training framework for semi-supervised landmark detection by fully considering the global shape constraint. Specifically, to ensure pseudo labels are reliable and consistent, a PCA-based shape model adjusts pseudo labels and eliminate abnormal ones. A novel Region Attention loss to make the network automatically focus on the structure consistent regions around pseudo labels. Extensive experiments show that our approach outperforms other semi-supervised methods and achieves notable improvement on three medical image datasets. Moreover, our framework is flexible and can be used as a plug-and-play module integrated into most supervised methods to improve performance further.