Curriculum Knowledge Switching for Pancreas Segmentation
This work addresses pancreas segmentation, a challenging medical imaging problem, with incremental improvements for domain-specific applications.
The authors tackled pancreas segmentation by proposing a Curriculum Knowledge Switching (CKS) framework that decomposes the task into phases of increasing difficulty, achieving state-of-the-art performance on the NIH dataset as measured by the DSC metric.
Pancreas segmentation is challenging due to the small proportion and highly changeable anatomical structure. It motivates us to propose a novel segmentation framework, namely Curriculum Knowledge Switching (CKS) framework, which decomposes detecting pancreas into three phases with different difficulty extent: straightforward, difficult, and challenging. The framework switches from straightforward to challenging phases and thereby gradually learns to detect pancreas. In addition, we adopt the momentum update parameter updating mechanism during switching, ensuring the loss converges gradually when the input dataset changes. Experimental results show that different neural network backbones with the CKS framework achieved state-of-the-art performance on the NIH dataset as measured by the DSC metric.