J Shanghai Jiaotong Univ Sci ›› 2025, Vol. 30 ›› Issue (4): 668-682.doi: 10.1007/s12204-024-2748-6

• • 上一篇    下一篇

CT-MFENet:基于全局-局部特征融合的用于视网膜血管分割的上下文Transformer和多尺度特征提取网络

  

  1. 昆明理工大学 信息工程与自动化学院,昆明 650500
  • 收稿日期:2023-10-30 接受日期:2024-02-05 出版日期:2025-07-31 发布日期:2025-07-31

CT-MFENet: Context Transformer and Multi-Scale Feature Extraction Network via Global-Local Features Fusion for Retinal Vessels Segmentation

邵党国,杨元彪,马磊,易三莉   

  1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China
  • Received:2023-10-30 Accepted:2024-02-05 Online:2025-07-31 Published:2025-07-31

摘要: 眼底视网膜血管的分割对于诊断眼部疾病至关重要。视网膜血管图像分割通常受到类别不平衡和血管尺度变化大的影响。这最终导致分割血管的不完整和连续性较差。本研究中,提出了CT-MFENet来解决上述问题。首先,使用上下文Transformer(CT)来整合上下文特征信息,这有助于像素间的远程建模,从而解决了血管连续性不完整的问题。其次,使用多尺度密集残差模块代替传统的CNN,以解决模型遇到多尺度血管时局部特征提取能力不足的问题。在解码阶段,引入的局部-全局融合模块增强了局部血管信息,并减小了高低级别特征之间的语义间隙。为了解决视网膜图像中的类别不平衡问题,提出一种混合损失函数,增强了模型对拓扑结构的分割能力。在公开的DRIVE、CHASEDB1、STARE和IOSTAR数据集上进行了实验。实验结果表明,提出的CT-MFENet在性能上优于大多数现有方法,包括基模型U-Net。

关键词: 视网膜血管分割, 上下文Transformer, 多尺度稠密残差, 混合损失函数, 全局-局部融合

Abstract: Segmentation of the retinal vessels in the fundus is crucial for diagnosing ocular diseases. Retinal vessel images often suffer from category imbalance and large scale variations. This ultimately results in incomplete vessel segmentation and poor continuity. In this study, we propose CT-MFENet to address the aforementioned issues. First, the use of context transformer (CT) allows for the integration of contextual feature information, which helps establish the connection between pixels and solve the problem of incomplete vessel continuity. Second, multi-scale dense residual networks are used instead of traditional CNN to address the issue of inadequate local feature extraction when the model encounters vessels at multiple scales. In the decoding stage, we introduce a local-global fusion module. It enhances the localization of vascular information and reduces the semantic gap between high- and low-level features. To address the class imbalance in retinal images, we propose a hybrid loss function that enhances the segmentation ability of the model for topological structures. We conducted experiments on the publicly available DRIVE, CHASEDB1, STARE, and IOSTAR datasets. The experimental results show that our CT-MFENet performs better than most existing methods, including the baseline U-Net.

中图分类号: