Li Zhenwei, Xu Mengying, Yang Xiaoli, Han Yanqi
College of Medical Technology and Engineering, Henan University of Science and Technology, Luoyang 471032, China.
Micromachines (Basel). 2022 Jun 15;13(6):947. doi: 10.3390/mi13060947.
Fundus diseases can cause irreversible vision loss in both eyes if not diagnosed and treated immediately. Due to the complexity of fundus diseases, the probability of fundus images containing two or more diseases is extremely high, while existing deep learning-based fundus image classification algorithms have low diagnostic accuracy in multi-labeled fundus images. In this paper, a multi-label classification of fundus disease with binocular fundus images is presented, using a neural network algorithm model based on attention mechanisms and feature fusion. The algorithm highlights detailed features in binocular fundus images, and then feeds them into a ResNet50 network with attention mechanisms to extract fundus image lesion features. The model obtains global features of binocular images through feature fusion and uses Softmax to classify multi-label fundus images. The ODIR binocular fundus image dataset was used to evaluate the network classification performance and conduct ablation experiments. The model's backend is the Tensorflow framework. Through experiments on the test images, this method achieved accuracy, precision, recall, and 1 values of 94.23%, 99.09%, 99.23%, and 99.16%, respectively.
眼底疾病如果不立即诊断和治疗，可导致双眼不可逆的视力丧失。由于眼底疾病的复杂性，眼底图像包含两种或更多种疾病的概率极高，而现有的基于深度学习的眼底图像分类算法在多标签眼底图像中的诊断准确率较低。本文提出了一种利用双目眼底图像进行眼底疾病多标签分类的方法，采用基于注意力机制和特征融合的神经网络算法模型。该算法突出双目眼底图像中的细节特征，然后将其输入到具有注意力机制的ResNet50网络中，以提取眼底图像病变特征。该模型通过特征融合获得双目图像的全局特征，并使用Softmax对多标签眼底图像进行分类。使用ODIR双目眼底图像数据集评估网络分类性能并进行消融实验。该模型的后端是Tensorflow框架。通过对测试图像的实验，该方法的准确率、精确率、召回率和F1值分别达到了94.23%、99.09%、99.23%和99.16%。
