基于跨层双线性池化的糖尿病视网膜病变分级算法研究

Research on grading algorithm of diabetic retinopathy based on cross-layer bilinear pooling

针对糖尿病视网膜病变(DR)分级任务中不同种类之间差异性微小特点,提出一种基于跨层双线性池化(CHBP)的视网膜病变分级算法。首先根据霍夫圆变换(HCT)对输入图像进行裁剪,再使用预处理方法提升图像对比度;然后以挤压激励分组残差网络(SEResNeXt)作为模型的主干,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训练,并采用中心损失(CL)和焦点损失(FL)方法进一步提升最终分类效果。实验结果显示,本文方法在印度糖尿病视网膜病变图像数据集(IDRiD)中二次加权卡帕系数(QWK)为90.84%,在梅西多数据集(Messidor-2)中受试者工作特征曲线下的面积(AUC)为88.54%。实验证明,本文提出的算法在糖尿病视网膜病变分级领域具有一定应用价值。

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.