| Summary: | INTRODUCTION: Diabetic eye disease (DED) is a group of eye problems that can affect diabetic people. Such disorders include diabetic retinopathy, diabetic macular edema, cataracts, and glaucoma. Diabetes can damage your eyes over time, which can lead to poor vision or even permanent blindness. Early detection of DED symptoms is therefore essential to prevent escalation of the disease and timely treatment. Research difficulties in early detection of DEDs can so far be summarized as follows: changes in the eye anatomy during its early stage are often untraceable by the human eye due to the subtle nature of the features, where large volumes of fundus images put tremendous pressure on scarce specialist resources, making manual analysis practically impossible.OBJECTIVES: Therefore, methods focused on deep learning have been practiced to promote early detection of DEDs and address the issues currently faced. Despite promising, highly accurate identification of early anatomical changes in the eye using Deep Learning remains a challenge in wide-scale practical application.METHODS: We present conceptual system architecture with pre-trained Convolutional Neural Network combined with image processing techniques to construct an early DED detection system. The data was collected from various publicly available sources, such as Kaggle, Messidor, RIGA, and HEI-MED. The analysis was presented with 13 Convolutional Neural Networks models, trained and tested on a wide-scale imagenet dataset using the Transfer Learning concept. Numerous techniques for improving performance were discussed, such as (i) image processing,(ii) fine-tuning, (iii) volume increase in data. The parameters were recorded against the default Accuracy metric for the test dataset.RESULTS: After the extensive study about the various classification system, and its methods, we found that creating an efficient neural network classifier demands careful consideration of both the network architecture and the data input. Hence, image processing plays a significant role to develop high accuracy diabetic eye disease classifiers.CONCLUSION: This article recognized specific work limitations in the early classification of diabetic eye disease. First, early-stage classification of DED, and second, classification of DR, GL, and DME using a method that causes permanent blindness afterward. Lastly, this study was intended to propose the framework for early automatic DED detection of fundus images through deep learning addressing three main research gaps.
|
|---|
