Faculty of Medicine at the University of Iceland, Sæmundargata 2, Reykjavík, 102, Iceland; Faculty of Electrical and Computer Engineering at the University of Iceland, Sæmundargata 2, Reykjavík, 102, Iceland.
Faculty of Medicine at the University of Iceland, Sæmundargata 2, Reykjavík, 102, Iceland.
Comput Methods Programs Biomed. 2022 Apr;216:106650. doi: 10.1016/j.cmpb.2022.106650. Epub 2022 Jan 23.
Retinal vessels provide valuable information when diagnosing or monitoring various diseases affecting the retina and disorders affecting the cardiovascular or central nervous systems. Automated retinal vessel segmentation can assist clinicians and researchers when interpreting retinal images. As there are differences in both the structure and function of retinal arteries and veins, separating these two vessel types is essential. As manual segmentation of retinal images is impractical, an accurate automated method is required.
In this paper, we propose a convolutional neural network based on serially connected U-nets that simultaneously segment the retinal vessels and classify them as arteries or veins. Detailed ablation experiments are performed to understand how the major components contribute to the overall system's performance. The proposed method is trained and tested on the public DRIVE and HRF datasets and a proprietary dataset.
The proposed convolutional neural network achieves an F score of 0.829 for vessel segmentation on the DRIVE dataset and an F score of 0.814 on the HRF dataset, consistent with the state-of-the-art methods on the former and outperforming the state-of-the-art on the latter. On the task of classifying the vessels into arteries and veins, the method achieves an F score of 0.952 for the DRIVE dataset exceeding the state-of-the-art performance. On the HRF dataset, the method achieves an F score of 0.966, which is consistent with the state-of-the-art.
The proposed method demonstrates competitive performance on both vessel segmentation and artery vein classification compared with state-of-the-art methods. The method outperforms human experts on the DRIVE dataset when classifying retinal images into arteries, veins, and background simultaneously. The method segments the vasculature on the proprietary dataset and classifies the retinal vessels accurately, even on challenging pathological images. The ablation experiments which utilize repeated runs for each configuration provide statistical evidence for the appropriateness of the proposed solution. Connecting several simple U-nets significantly improved artery vein classification performance. The proposed way of serially connecting base networks is not limited to the proposed base network or segmenting the retinal vessels and could be applied to other tasks.
视网膜血管在诊断或监测影响视网膜的各种疾病以及影响心血管或中枢神经系统的疾病时提供了有价值的信息。自动视网膜血管分割可以帮助临床医生和研究人员解读视网膜图像。由于视网膜动脉和静脉在结构和功能上存在差异，因此将这两种血管类型分开是至关重要的。由于手动分割视网膜图像不切实际，因此需要一种准确的自动方法。
在本文中，我们提出了一种基于串联 U 型网络的卷积神经网络，该网络可以同时分割视网膜血管并将其分类为动脉或静脉。进行了详细的消融实验，以了解主要组件如何影响整个系统的性能。该方法在公共 DRIVE 和 HRF 数据集以及专有数据集上进行了训练和测试。
所提出的卷积神经网络在 DRIVE 数据集上的血管分割任务中获得了 0.829 的 F 分数，在 HRF 数据集上获得了 0.814 的 F 分数，与前者的最新方法一致，并且在后者中表现优于最新方法。在将血管分类为动脉和静脉的任务中，该方法在 DRIVE 数据集上的 F 分数达到 0.952，超过了最新方法的性能。在 HRF 数据集上，该方法的 F 分数达到 0.966，与最新方法一致。
与最新方法相比，所提出的方法在血管分割和动脉静脉分类任务上均表现出竞争力。在同时将视网膜图像分类为动脉、静脉和背景时，该方法在 DRIVE 数据集上的表现优于人类专家。该方法分割专有数据集上的脉管系统，并准确分类视网膜血管，即使在具有挑战性的病理图像上也是如此。利用每个配置重复运行的消融实验为提出的解决方案的适当性提供了统计证据。连接几个简单的 U 型网络显著提高了动脉静脉分类性能。所提出的串联基础网络的方法不仅限于所提出的基础网络或分割视网膜血管，也可以应用于其他任务。
