Abstract
Medical imaging plays a vital role as an auxiliary tool in clinical diagnosis and treatment, with segmentation serving as a crucial foundational process in medical image analysis. Nonetheless, challenges such as class imbalance and indistinct boundaries of regions of interest (ROIs) often complicate medical image segmentation. Constructing a network capable of precisely locating small ROIs and achieving precise segmentation is a significant task. In this paper, we propose a boundary information-enhanced local-global collaborative network. This network leverages the local feature extraction capabilities of CNNs, the global feature recognition prowess of state space models exemplified by Mamba, and boundary feature enhancement to learn a more comprehensive representation. Specifically, we propose a local-global collaborative encoder via attention fusion. This encoder adeptly integrates local and global features through a deep attention fusion module to address the challenge of segmenting small ROIs in class-imbalanced scenarios. Subsequently, we develop a boundary information-enhanced decoder. Through the incremental implementation of boundary attention modules, this decoder emphasizes boundary features during image restoration, steering the network to achieve more complete segmentation. Extensive experiments on various public class-imbalanced medical image segmentation datasets demonstrate that the proposed BELGNet outperforms state-of-the-art methods.