Deep learning based retinal vessel segmentation and hypertensive retinopathy quantification using heterogeneous features cross-attention neural network.

基于深度学习的视网膜血管分割和使用异构特征交叉注意神经网络的高血压视网膜病变量化。

• 影响指数: 5.058
• 发表时间: 2024
• 来源期刊: Front Med (Lausanne)
• DOI: 10.3389/fmed.2024.1377479
• PMID: 38841586
• 文章类型: Journal Article
• 作者列表: Liu X,Tan H,Wang W,Chen Z

关键词: color fundus images; cross-attention network; deep learning; hypertensive retinopathy quantification; retinal vessel segmentation

Abstract

Retinal vessels play a pivotal role as biomarkers in the detection of retinal diseases, including hypertensive retinopathy. The manual identification of these retinal vessels is both resource-intensive and time-consuming. The fidelity of vessel segmentation in automated methods directly depends on the fundus images\' quality. In instances of sub-optimal image quality, applying deep learning-based methodologies emerges as a more effective approach for precise segmentation. We propose a heterogeneous neural network combining the benefit of local semantic information extraction of convolutional neural network and long-range spatial features mining of transformer network structures. Such cross-attention network structure boosts the model\'s ability to tackle vessel structures in the retinal images. Experiments on four publicly available datasets demonstrate our model\'s superior performance on vessel segmentation and the big potential of hypertensive retinopathy quantification.

摘要

视网膜血管在视网膜疾病的检测中作为生物标志物发挥着关键作用,包括高血压视网膜病变.这些视网膜血管的手动识别是资源密集型和耗时的。自动方法中血管分割的保真度直接取决于眼底图像的质量。在图像质量次优的情况下，应用基于深度学习的方法成为一种更有效的精确分割方法。我们提出了一种异构神经网络，结合卷积神经网络的局部语义信息提取和变压器网络结构的远程空间特征挖掘的好处。这种交叉注意力网络结构增强了模型处理视网膜图像中血管结构的能力。在四个公开数据集上进行的实验证明了我们的模型在血管分割方面的优越性能和高血压视网膜病变量化的巨大潜力。