The impact of multi-class information decoupling in latent space on skin lesion segmentation

Noise, out-of-distribution (OOD) challenges, and boundary ambiguity are not only challenges in skin disease segmentation, but also difficulties in the field of medical image segmentation. Although various medical image segmentation networks have emerged, there are certain limitations in addressing these issues because previous research has neglected the expression of medical image features in latent space. In this article, we study the relationship between latent space information and medical image segmentation. We demonstrate that the decoupling of multi-class information in latent space is closely related to the accuracy of medical image segmentation. Therefore, this study proposes a new segmentation scheme - Contextual directional decoupling network (CodeNet), which aims to enhance feature representation by decoupling multi-class information in latent space, enabling the model to successfully address noise, artifacts, OOD challenges, and boundary ambiguity. Comprehensive experiments on four public datasets and one private dataset show that our proposed CodeNet is superior to other state-of-the-art models and achieves good performance on multiple commonly used metrics. This demonstrates the effectiveness of our method in skin lesion segmentation.