计算机与现代化 ›› 2024, Vol. 0 ›› Issue (05): 110-114.doi: 10.3969/j.issn.1006-2475.2024.05.019

• 图像处理 • 上一篇    下一篇

基于注意力机制的U-Net眼底图像分割算法

  



  1. (华东交通大学电气与自动化工程学院,江西 南昌 330013)
  • 出版日期:2024-05-29 发布日期:2024-06-12
  • 作者简介: 作者简介:张子旭(2001—),男,江西宜春人,本科生,研究方向:数字图像处理,机器学习,E-mail: 1273363671@qq.com; 李嘉莹(2003—),女,本科生, 研究方向:数字图像处理,机器学习,E-mail: 1106725273@qq.com; 栾鹏鹏(1998—),男,硕士研究生,研究方向:深度学习,E-mail: 1160403031@qq.com; 通信作者:彭圆圆(1987—),男,湖北武穴人,讲师,博士,研究方向:图像处理,模式识别,人工智能,E-mail: 2437570542@qq.com。
  • 基金资助:
    江西省大学生创新创业项目(202310404008)
       

An Attention Mechanism-based U-Net Fundus Image Segmentation Algorithm



  1. (School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013, China)
  • Online:2024-05-29 Published:2024-06-12

摘要:
摘要:视网膜眼底血管的半径、宽度等是评估眼部疾病的重要指标,因此精确分割眼底图像具有十分重要的意义。为了有效辅助医生诊断眼部疾病,本文提出一种新的神经网络分割眼底血管图像,基本思想是通过改进传统的U-Net模型,借助一种注意力融合机制,使用Transformer构建通道注意力机制和空间注意力机制,将2个注意力机制获取的信息进行融合,减少信息的丢失。此外,视网膜眼底图像的数量比较少,神经网络的系数比较大,训练时容易发生过拟合,所以引入DropBlock层解决此难题。在公开数据集DRIVE上面进行验证,与多种最新的方法进行对比,本文提出的方法获得最高的ACC值0.967和最高的F1值0.787。实验结果表明,本文提出的方法能够有效地分割眼底图像。



关键词: 关键词:视网膜眼底图像分割, 注意力机制, DropOut层

Abstract: Abstract: The radius and width of retinal fundus vessels are important indicators for assessing eye diseases, so accurate segmentation of fundus images is becoming increasingly meaningful. In order to effectively assist doctors in diagnosing eye diseases, the paper proposes a new neural network to segment fundus vascular images. The basic idea is to reduce the information loss by improving the traditional U-Net model with the help of an attention fusion mechanism, using Transformer to construct a channel attention mechanism and a spatial attention mechanism, and fusing the information obtained by the two attention mechanisms. In addition, the number of retinal fundus images is relatively small, and the coefficients of the neural network are relatively large, which are prone to overfitting during training, so the DropBlock layer is introduced to solve this problem. The proposed method was validated on the publicly available dataset DRIVE and compared with several state-of-the-art methods. The results show that our method achieved the highest ACC value of 0.967 and the highest F1 value of 0.787. These experimental results demonstrate that the proposed method is effective in segmenting retinal fundus images.

Key words: Key words: retinal fundus image segmentation, attention mechanism, DropOut layer

中图分类号: