Authors: Wan Jialong, Hu Jianbin, Jin Weidong, Tang Peng
To construct an intelligent analysis system based on visual attention for diabetic retinopathy (DR) assistant diagnosis and to realize the automatic screening and grading of fundus images of DR.
Total of 35 126 DR fundus images were downloaded from the Diabetic Retinopathy Detection competition in the Data Modeling and Data Analysis Competition Platform (Kaggle), and 1 200 fundus images were downloaded from the Messidor website.Firstly, according to the characteristics of DR fundus images, a series of preprocessing was carried out for retina images.Then, on the basis of VGG16 network, visual attention SENet module was introduced to improve the saliency of lesion features, and a deep convolution neural network SEVGG with complex network structure was generated.The network basically inherited some structural parameters of VGG16, and the parameters of SENet module were adjusted according to the basic network and training data set.Finally, the SEVGG network model was used to screen the DR fundus image, and the fundus image was divided into different levels according to the degree of lesions of DR in different periods.Configure the training platform and environment and perform algorithm performance verification experiments.
The method proposed in this study was tested on different open standard datasets, and finally achieved high accuracy in image-based classification.The accuracy of 5 classification in Kaggle dataset was 83%, the sensitivity of lesion detection was 99.86% and the specificity was 99.63%.The accuracy rate of the 4 classification in the Messidor data set was up to 88%, the sensitivity of the lesion detection was 98.17%, and the specificity was 96.39%.The introduction of visual attention was more significant for the focus of the lesion, which helped the accurate detection of DR.
This method effectively avoids some shortcomings of traditional artificial feature extraction and fundus image classification, and is more accurate for lesion recognition.It is not only superior to the previous method, but also shows better robustness and generalization.