Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 8 (2022) > Article

DOI: 10.14704/nq.2022.20.8.NQ44600

MACHINE LEARNING BASED CLASSIFICATION OF DIABETES MACULAR EDEMA DISEASE OVER RETINAL IMAGES

CHRISTOPHER PAUL A, ANURADHA B, KAVITHA M S

Abstract

Patients with diabetes are more likely to experience complications in their eyesight. The retina is damaged in diabetic retinopathy (DR), the macula is damaged in diabetic macular edema (DME), and the optic disk is damaged in severe glaucoma, both of which lead to vision loss. However, early symptoms are scarce because of the gradual course of eye diseases, making diagnosis challenging. This means an early detection and screening procedure needs to be supported by a completely automated system. In this paper, we develop a convolutional neural network (CNN) model, which is used to localisation of the images and then the classification of the localised regions in an image. The study uses Artificial Neural Network for localisation and CNN for classification. The simulation is conducted on different diabetic retinal image datasets that includes ORIGA, MESSIDOR and DRHAGIS. The simulation is conducted in terms of accuracy, precision, recall and f-measure. The results show that the proposed classification model achieves higher accuracy than the testing results

Keywords

Diabetic patients, diabetic retinopathy, Machine learning, classification

Full Text

PDF

References

?>