河北大学学报(自然科学版) ›› 2025, Vol. 45 ›› Issue (4): 408-418.DOI: 10.3969/j.issn.1000-1565.2025.04.009

• • 上一篇    下一篇

基于并行Mamba的轻量化息肉图像分割

贾承富1,2,孙晓川1,2,贾敬好3,陈伟彬3,李莹琦1,2   

  • 收稿日期:2024-09-06 出版日期:2025-07-25 发布日期:2025-07-11
  • 通讯作者: 李莹琦(1984—)
  • 作者简介:贾承富(1999—),男,华北理工大学在读硕士研究生,主要从事内窥镜息肉图像分割、深度学习算法方向研究.
    E-mail:jiachengfu@stu.ncst.edu.cn
  • 基金资助:
    国家自然科学基金项目(62276143)

Lightweight polyp image segmentation based on parallel Mamba

JIA Chengfu1,2, SUN Xiaochuan1,2, JIA Jinghao3, CHEN Weibin3, LI Yingqi1,2   

  1. 1. College of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, China; 2. Hebei Key Laboratory of Industrial Intelligent Sensing, Tangshan 063210, China; 3. North China University of Science and Technology Affiliated Hospital, Tangshan 063210, China
  • Received:2024-09-06 Online:2025-07-25 Published:2025-07-11

摘要: 针对现有分割方法难以兼顾分割精度和复杂度的问题,提出了一种新型轻量化结直肠息肉图像分割网络MCANet(Mamba and convolutional attention network).该网络的核心在于级联了空间注意力和通道注意力的多尺度卷积注意力模块,通过融合多尺度特征,以缩减浅层和深层特征之间的差距.此外,引入了并行Mamba模块,利用并行化计算的方式提高运算效率.在3个公共数据集上的实验结果表明,所提出的方法在有效性和泛化方面都优于其他先进的方法,使其能够精准地定位结直肠中的异常部分,为临床医师提供关键的决策支持,从而降低了息肉癌变的风险.

关键词: 轻量级的网络, 息肉分割, 深度学习, Mamba, 多尺度注意力机制

Abstract: To address the challenge of balancing segmentation accuracy and complexity in existing segmentation methods, a novel lightweight colorectal polyp image segmentation network, MCANet(Mamba and convolutional attention network), is proposed. The core of this network lies in a multiscale convolutional attention module cascading spatial and channel attention by fusing multiscale features in order to reduce the gap between shallow and deep features. In addition, a parallel Mamba module is introduced to improve the computational efficiency by utilizing parallelized computation. Experimental results on three public datasets show that the proposed method outperforms other state-of-the-art methods in terms of effectiveness and generalization, enabling it to pinpoint the abnormal portions in the colorectum and provide clinicians with critical decision support, which reduces the risk of polyp cancer.

Key words: lightweight network, polyp segmentation, deep learning, Mamba, multi-scale attention module

中图分类号: