欢迎访问《图学学报》 分享到：
图学学报

图学学报 ›› 2022, Vol. 43 ›› Issue (2): 273-278.DOI: 10.11996/JG.j.2095-302X.2022020273

• 图像处理与计算机视觉 • 上一篇    下一篇

融合边缘增强注意力机制和 U-Net 网络的医学图像分割

  

  1. 1. 北方民族大学计算机科学与工程学院，宁夏 银川 750021；
    2. 国家民委图像图形智能处理实验室，宁夏 银川 750021
  • 出版日期:2022-04-30 发布日期:2022-05-07
  • 基金资助:

    国家自然科学基金项目(61762003，62162001)；

    中国科学院“西部之光”人才培养引进计划(JF2012c016-2)；

    宁夏优秀人才支持计划；

    宁夏自然科学基金项目(2022AAC02041)

A U-Net based contour enhanced attention for medical image segmentation

  1. 1. School of Computer Science and Engineering, North Minzu University, Yinchuan Ningxia 750021, China;
    2. The Key Laboratory of Images & Graphics Intelligent Processing of State Ethnic Affairs Commission, Yinchuan Ningxia 750021, China

  • Online:2022-04-30 Published:2022-05-07
  • Supported by:

    National Natural Science Foundation of China (61762003, 62162001); 

    “Light of the West” Talent Training and Introduction Program of Cas (JF2012c016-2); 

    Ningxia Excellent Talents Support Program; 

    Ningxia Natural Science Foundation Project (2022AAC02041)

PDF (PC)

681

摘要： 医学图像分割是医学图像处理领域中的关键步骤，随着深度学习技术的逐步深入，图像分割技
术有了突飞猛进的发展。然而，在分割过程中，病灶特征的边缘像素点划分仍存在模糊、不准确的问题。为此，
提出一种边缘增强的注意力模块(CEA)，分别进行水平和垂直 2 个不同方向的特征编码捕获位置信息，并通过
计算位置特征和输入特征之间的偏移量加强边缘信息。将该模块应用基于 U-Net 的医学图像分割网络中，可突
破卷积核的空间限制，捕获具有位置感知的跨通道信息及更加明确的边缘轮廓信息，从而提高分割的准确性。
在公开数据集 Kvasir-SEG 上的定量对比实验表明，加入注意力模块的网络在 Dice、精确度、召回率等指标上
均取得了更好的结果，可有效改善医学图像分割效果。

关键词: 医学图像分割, 位置信息, 注意力机制, 边缘轮廓, 边界差异

Abstract: Medical image segmentation is vital for medical image processing. With the development of deep learning,
image segmentation techniques have achieved remarkable development. However, there remain fuzzy and inaccurate
problems in the discrimination of contour pixels for lesion features. To address the problems, we proposed a contour
enhanced attention (CEA) module. It can obtain rich location information by feature encoding in two different
directions and strengthen contours by calculating the offset between location features and input features. Furthermore,
we constructed a U-Net for medical image segmentation based on the proposed module, it can break through the space
limitation of convolution kernel, thus capturing position-aware cross-channel information and clearer edge contour
information. In doing so, the accuracy of segmentation can be improved. Experiments on the public Kvasir-SEG dataset demonstrates that the network with CEA module achieves better results in Dice, precision, recall rate, and
other evaluation indexes in medical segmentation.


Key words: medical image segmentation, location information, attention mechanism, edge contour, contour
differences

中图分类号: