Abstract
Non-proliferative diabetic retinopathy (NPDR) is an early stage of diabetic retinopathy. Effective testing can stop the disease from developing. In this paper, a 7-layer convolutional neural network after migration learning based on MATLAB R2017a, was used to perform image recognition on the full-eye OCT images of normal and NPDR at various stages. The full-eye OCT images for the testing set and training set were obtained from an open source database at duke university. A total of 120 images were obtained by optical coherence tomography. There were four types of images, including 30 OCT images of normal, NPDR type 1, NPDR type 2 and NPDR type 3. We labeled 120 full-eye OCT images numerically and divided them into a training set and a testing set, 60 each. The first 15 pictures of each category are used as the training set, and the last 15 pictures are used as the testing set. Four images were randomly selected from the 60 testing set images to determine which of the four categories the extracted full-eye OCT images were. Finally, the accuracy of the convolutional neural network after transfer learning reaches the expected effect.
Sign-in/Register to access full text options 
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.
