Che Zhihao, Bi Fukun, Sun Yu, Xing Weiying, Huang Hui, Zhang Xinyue
School of Information Science and Technology, North China University of Technology, Beijing, China.
School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing, China.
Heliyon. 2023 Jul 25;9(8):e18605. doi: 10.1016/j.heliyon.2023.e18605. eCollection 2023 Aug.
Diabetes can induce diabetic retinopathy (DR), and the blindness caused by this disease is irreversible. The early analysis of mouse retinal images, including the layer and cell segmentation properties of these images, can help to effectively diagnose this disease.
In the study, we design a dilated residual method based on a feature pyramid network (FPN), in which the FPN is adopted as the base network for solving the multiscale segmentation problem concerning mouse retinal images. In the bottom-up encoding pathway, we construct our backbone feature extraction network via the combination of dilated convolution and a residual block, further increasing the range of the receptive field to obtain more context information. At the same time, we integrate a squeeze-and-excitation (SE) attention module into the backbone network to obtain more small object details. In the top-down decoding pathway, we replace the traditional nearest-neighbor upsampling method with the transposed convolution method and add a segmentation head to obtain semantic segmentation results.
The effectiveness of our network model is verified in two segmentation tasks: ganglion cell segmentation and mouse retinal cell and layer segmentation. The outcomes demonstrate that, compared to other supervised segmentation methods based on deep learning, our model attains the utmost precision in both binary segmentation and multiclass semantic segmentation tasks.
The dilated residual FPN is a robust method for mouse retinal image segmentation and it can effectively assist DR diagnosis.
糖尿病可引发糖尿病性视网膜病变（DR），该疾病导致的失明是不可逆的。对小鼠视网膜图像进行早期分析，包括这些图像的层和细胞分割特性，有助于有效诊断该疾病。
在本研究中，我们设计了一种基于特征金字塔网络（FPN）的扩张残差方法，其中采用FPN作为基础网络来解决小鼠视网膜图像的多尺度分割问题。在自底向上的编码路径中，我们通过扩张卷积和残差块的组合构建主干特征提取网络，进一步扩大感受野范围以获取更多上下文信息。同时，我们将挤压激励（SE）注意力模块集成到主干网络中以获取更多小目标细节。在自顶向下的解码路径中，我们用转置卷积方法取代传统的最近邻上采样方法，并添加一个分割头以获得语义分割结果。
我们的网络模型在两项分割任务中得到验证：神经节细胞分割以及小鼠视网膜细胞和层分割。结果表明，与其他基于深度学习的监督分割方法相比，我们的模型在二值分割和多类语义分割任务中均达到最高精度。
扩张残差FPN是一种用于小鼠视网膜图像分割的稳健方法，能够有效辅助DR诊断。
