Liang Liming, Peng Renjie, Feng Jun, Yin Jiang
School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, P. R. China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2022 Oct 25;39(5):928-936. doi: 10.7507/1001-5515.202104038.
Considering the small differences between different types in the diabetic retinopathy (DR) grading task, a retinopathy grading algorithm based on cross-layer bilinear pooling is proposed. Firstly, the input image is cropped according to the Hough circle transform (HCT), and then the image contrast is improved by the preprocessing method; then the squeeze excitation group residual network (SEResNeXt) is used as the backbone of the model, and a cross-layer bilinear pooling module is introduced for classification. Finally, a random puzzle generator is introduced in the training process for progressive training, and the center loss (CL) and focal loss (FL) methods are used to further improve the effect of the final classification. The quadratic weighted Kappa (QWK) is 90.84% in the Indian Diabetic Retinopathy Image Dataset (IDRiD), and the area under the receiver operating characteristic curve (AUC) in the Messidor-2 dataset (Messidor-2) is 88.54%. Experiments show that the algorithm proposed in this paper has a certain application value in the field of diabetic retina grading.
考虑到糖尿病视网膜病变（DR）分级任务中不同类型之间的细微差异，提出了一种基于跨层双线性池化的视网膜病变分级算法。首先，根据霍夫圆变换（HCT）裁剪输入图像，然后通过预处理方法提高图像对比度；接着，将挤压激励组残差网络（SEResNeXt）用作模型的主干，并引入跨层双线性池化模块进行分类。最后，在训练过程中引入随机拼图生成器进行渐进式训练，并使用中心损失（CL）和焦点损失（FL）方法进一步提高最终分类的效果。在印度糖尿病视网膜病变图像数据集（IDRiD）中，二次加权卡帕（QWK）为90.84%，在梅西多-2数据集（Messidor-2）中，受试者工作特征曲线下面积（AUC）为88.54%。实验表明，本文提出的算法在糖尿病视网膜分级领域具有一定的应用价值。
