作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2024, Vol. 50 ›› Issue (4): 286-293. doi: 10.19678/j.issn.1000-3428.0067779

• 开发研究与工程应用 • 上一篇    下一篇

改进U-Net的多级边缘增强医学图像分割网络

胡帅, 李华玲, 郝德琛   

  1. 中北大学软件学院, 山西 太原 030051
  • 收稿日期:2023-06-02 修回日期:2023-07-14 发布日期:2024-04-13
  • 通讯作者: 李华玲,E-mail:lihualing750108@163.com E-mail:lihualing750108@163.com
  • 基金资助:
    辽宁省自然科学基金(2022-KF-22-13);山西省重点研发计划(202102020101009);中北大学科技立项项目(20221858)。

Improved Multistage Edge-Enhanced Medical Image Segmentation Network of U-Net

HU Shuai, LI Hualing, HAO Dechen   

  1. College of Software, North University of China, Taiyuan 030051, Shanxi, China
  • Received:2023-06-02 Revised:2023-07-14 Published:2024-04-13

摘要: 医学图像分割精度对医师临床诊疗起到关键作用,但由于医学图像的复杂性以及目标区域的多样性,造成现有医学图像分割方法存在边缘区域分割不完整和上下文特征信息利用不充分的问题。为此,提出一种改进U-Net的多级边缘增强(MEE)医学图像分割网络(MDU-Net)模型。首先,在编码器结构中加入提取双层低级特征信息的MEE模块,通过不同扩张率的扩张卷积块获取特征层中丰富的边缘信息。其次,在跳跃连接中嵌入融合相邻层特征信息的细节特征关联(DFA)模块,以获取深层次和多尺度的上下文特征信息。最后,在解码器结构对应特征层中聚合不同模块所提取的特征信息,通过上采样操作得到最终的分割结果。在2个公开数据集上的实验结果表明,与用于医学图像分割的Transformers强编码器(TransUNet)等模型相比,MDU-Net模型能够高效使用医学图像中不同特征层的特征信息,并在边缘区域取得了更好的分割效果。

关键词: 医学图像分割, 多级边缘增强模块, 注意力模块, 多尺度特征, 深度学习

Abstract: Medical image segmentation accuracy plays a key role in clinical diagnosis and treatment. However, because of the complexity of medical images and diversity of target regions, existing medical image segmentation methods are limited to incomplete edge region segmentation and insufficient use of image context feature information. An improved Multistage Edge-Enhanced(MEE) medical image segmentation network of the U-Net, known as MDU-Net model, is proposed to solve these problems. First, a MEE module is added to the encoder structure to extract double-layer low-stage feature information, and the rich edge information in the feature layer is obtained by expanding the convolution blocks at different expansion rates. Second, a Detailed Feature Association(DFA) module integrating the feature information of adjacent layers is embedded in the skip connection to obtain deep-stage and multiscale context feature information. Finally, the feature information extracted from the different modules is aggregated in the corresponding feature layer of the decoder structure, and the final segmentation result is obtained by an upsampling operation. The experimental results on two public datasets show that compared with other models, such as Transformers make strong encoders for medical image segmentation(TransUNet), the MDU-Net model can efficiently use the feature information of different feature layers in medical images and achieve an improved segmentation effect in the edge region.

Key words: medical image segmentation, Multistage Edge-Enhanced(MEE) module, attention module, multiscale feature, deep learning

中图分类号: