Diabetic Retinopathy Detection Using Optimization Assisted Deep Learning Model: Outlook on Improved Grey Wolf Algorithm

In recent days, study on retinal image remains a significant area for analysis. Several retinal diseases are identified by examining the differences occurring in the retina. Anyhow, the major shortcoming between these analyses was that the identification accuracy is not satisfactory. The adopted framework includes two phases namely; (i) feature extraction and (ii) classification. Initially, the input fundus image is subjected to the feature extraction process, where the features like Local Binary Pattern (LBP), Local Vector Pattern (LVP) and Local Tetra Patterns (LTrP) are extracted. These extracted features are subjected to the classification process, where the Deep Belief Network (DBN) is used as the classifier. In addition, to improve the accuracy, the activation function and hidden neurons of DBN are optimally tuned by means of the Self Improved Grey Wolf Optimization (SI-GWO). Finally, the performance of implemented work is compared and proved over the conventional models.

Automated summary

Recent research has shown that the study of retinal images is crucial for identifying retinal diseases, but the accuracy still needs improvement. By using a two-phase process of feature extraction and classification, employing Deep Belief Network as the classifier, and optimizing with Self Improved Grey Wolf Optimization, the accuracy of identifying retinal diseases can be enhanced.