Centre of Intelligent Acoustics and Immersive Communications, School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, Shaanxi 710072, P.R. China.
Comput Methods Programs Biomed. 2021 Jun;205:106070. doi: 10.1016/j.cmpb.2021.106070. Epub 2021 Apr 1.
Retinal vessels are a major feature used for the physician to diagnose many retinal diseases, such as cardiovascular disease and Glaucoma. Therefore, the designing of an auto-segmentation algorithm for retinal vessel draw great attention in medical field. Recently, deep learning methods, especially convolutional neural networks (CNNs) show extraordinary potential for the task of vessel segmentation. However, most of the deep learning methods only take advantage of the shallow networks with a traditional cross-entropy objective, which becomes the main obstacle to further improve the performance on a task that is imbalanced. We therefore propose a new type of residual U-Net called Before-activation Squeeze-and-Excitation ResU-Net (BSEResu-Net) to tackle the aforementioned issues.
Our BSEResU-Net can be viewed as an encoder/decoder framework that constructed by Before-activation Squeeze-and-Excitation blocks (BSE Blocks). In comparison to the current existing CNN structures, we utilize a new type of residual block structure, namely BSE block, in which the attention mechanism is combined with skip connection to boost the performance. What's more, the network could consistently gain accuracy from the increasing depth as we incorporate more residual blocks, attributing to the dropblock mechanism used in BSE blocks. A joint loss function which is based on the dice and cross-entropy loss functions is also introduced to achieve more balanced segmentation between the vessel and non-vessel pixels.
The proposed BSEResU-Net is evaluated on the publicly available DRIVE, STARE and HRF datasets. It achieves the F1-score of 0.8324, 0.8368 and 0.8237 on DRIVE, STARE and HRF dataset, respectively. Experimental results show that the proposed BSEResU-Net outperforms current state-of-the-art algorithms.
The proposed algorithm utilizes a new type of residual blocks called BSE residual blocks for vessel segmentation. Together with a joint loss function, it shows outstanding performance both on low and high-resolution fundus images.
视网膜血管是医师诊断许多视网膜疾病（如心血管疾病和青光眼）的重要特征。因此，设计一种自动分割算法来分割视网膜血管引起了医学界的极大关注。最近，深度学习方法，特别是卷积神经网络（CNNs），在血管分割任务中显示出了非凡的潜力。然而，大多数深度学习方法仅利用具有传统交叉熵目标的浅层网络，这成为进一步提高任务性能的主要障碍，因为该任务是不平衡的。因此，我们提出了一种新型的残差 U-Net，称为激活前挤压激励残差 U-Net（BSEResu-Net），以解决上述问题。
我们的 BSEResu-Net 可以看作是一个由激活前挤压激励块（BSE 块）构建的编码器/解码器框架。与当前现有的 CNN 结构相比，我们在网络中使用了一种新型的残差块结构，即 BSE 块，其中注意力机制与跳跃连接相结合，以提高性能。此外，由于在 BSE 块中使用了 Dropblock 机制，网络可以随着残差块数量的增加而持续获得更高的精度。此外，还引入了一种基于骰子和交叉熵损失函数的联合损失函数，以实现血管和非血管像素之间更平衡的分割。
所提出的 BSEResu-Net 在公开的 DRIVE、STARE 和 HRF 数据集上进行了评估。在 DRIVE、STARE 和 HRF 数据集上，它分别获得了 0.8324、0.8368 和 0.8237 的 F1 分数。实验结果表明，所提出的 BSEResu-Net 优于当前最先进的算法。
所提出的算法使用了一种新型的残差块，称为 BSE 残差块，用于血管分割。结合联合损失函数，它在低分辨率和高分辨率眼底图像上都表现出了出色的性能。
