A Domain Knowledge-Based Semi-supervised Pancreas Segmentation Approach

The five-year survival rate of pancreatic cancer is extremely low, and the survival time of patients can be extended by timely detection and treatment. Deep learning-based methods have been used to assist radiologists in diagnosis, with remarkable achievements. However, obtaining sufficient labeled data is time-consuming and labor-intensive. Semi-supervised learning is an effective way to alleviate dependence on annotated data by combining unlabeled data. Since the existing semi-supervised pancreas segmentation works are easier to ignore the domain knowledge, leading to location and shape bias. In this paper, we propose a semi-supervised pancreas segmentation method based on domain knowledge. Specifically, the prior constraints for different organ sub-regions are used to guide the pseudo-label generation for unlabeled data. Then the bidirectional information flow regularization is designed by further utilizing pseudo-labels, encouraging the model to align the labeled and unlabeled data distributions. Extensive experiments on NIH pancreas datasets show: the proposed method achieved Dice of 76.23% and 80.76% under 10% and 20% labeled data, respectively, which is superior to other semi-supervised pancreas segmentation methods.