Abstract
Diabetic retinopathy (DR) is one of the major complications caused by diabetes and can lead to severe vision loss or even complete blindness if not diagnosed and treated in a timely manner. In this paper, a new feature map global channel attention mechanism (GCA) is proposed to solve the problem of the early detection of DR. In the GCA module, an adaptive one-dimensional convolution kernel size algorithm based on the dimension of the feature map is proposed and a deep convolutional neural network model for DR color medical image severity diagnosis named GCA-EfficientNet (GENet) is designed. The training process uses transfer learning techniques with a cosine annealing learning rate adjustment strategy. The image regions of interest of GENet are visualized using a heat map. The final accuracy, precision, sensitivity and specificity of the DR dataset of the Kaggle competition reached 0.956, 0.956, 0.956, and 0.989, respectively. A large number of experiment results show that GENet based on the GCA attention mechanism can more effectively extract lesion features and classify the severity of DR.
Highlights
Diabetic retinopathy (DR) is one of the major complications of diabetes due to retinal damage caused by rupture of capillaries from high levels of sugar [1]
Unlike the SE structure and Efficient Channel Attention (ECA) structure, the global channel attention mechanism (GCA) structure proposed in this paper overcomes both the loss of feature map channel information caused by the dimensionality reduction processing in the SE structure and the drawback of failing to consider the global channel correlation in the ECA structure, while the adaptive convolution kernel size adjustment method proposed in this paper can extract local channel correlation information at different scales according to the feature maps of different tasks
The deep convolutional neural network model used in this paper is based on EfficientNet [41], which is based on the neural network architecture search technique (NAS) obtained by balancing the network width, depth and input image resolution, using a relatively small number of parameters but obtaining better performance, depending on the different resolutions of the input image, model width and depths, EfficientNet can be divided into eight models from EfiicientNet-B0 to EfficientNet-B7 [41].EfficientNet-B7 exceeds the accuracy achieved by the best GPipe at that time, but with 8.4 times less number of parameters and 6.1 times faster computing speed [41]
Summary
Diabetic retinopathy (DR) is one of the major complications of diabetes due to retinal damage caused by rupture of capillaries from high levels of sugar [1]. When using DCNN for DR classification, due to the fact that color fundus images are rich in detailed parts such as capillaries and are spread over the vast majority of the image, proper preprocessing of the original image is required, and more importantly, the network model needs to consider the relevance of the original image at different locations and in different channels. This requires the network to introduce a proper attention mechanism, which makes the model adaptively enhance the perception of useful information. The main contribution points of this paper as follows. (1) For the DR severity classification problem, a Global Channel Attention (GCA) mechanism is proposed to update the attention weights among different channels of the feature map with the model training process. (2) In the process of GCA module parameter update, an adaptive one-dimensional convolution kernel size calculation method is proposed to adjust the size of the convolution kernel adaptively according to the dimensions of the feature maps of different feature extraction modules. (3) Combining the GCA attention mechanism and EfficientNet, the GCA-EfficientNet (GENet) model is proposed, and based on the transfer learning technique, the training of the model is accomplished, and the accuracy, sensitivity and specificity reach 0.956, 0.956 and 0.989 respectively on the DR dataset of the kaggle competition
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
