Modelling on-demand preprocessing framework towards practical approach in clinical analysis of diabetic retinopathy

<p>Diabetic retinopathy (DR) refers to a complication of diabetes and a prime cause of vision loss in middle-aged people. A timely screening and diagnosis process can reduce the risk of blindness. Fundus imaging is mainly preferred in the clinical analysis of DR. However; the raw fundus images are usually subjected to artifacts, noise, low and varied contrast, which is very hard to process by human visual systems and automated systems. In the existing literature, many solutions are given to enhance the fundus image. However, such approaches are particular and limited to a specific objective that cannot address multiple fundus images. This paper has presented an on-demand preprocessing frame work that integrates different techniques to address geometrical issues, random noises, and comprehensive contrast enhancement solutions. The performance of each preprocessing process is evaluated against peak signal-to-noise ratio (PSNR), and brightness is quantified in the enhanced image. The motive of this paper is to offer a flexible approach of preprocessing mechanism that can meet image enhancement needs based on different preprocessing requirements to improve the quality of fundus imaging towards early-stage diabetic retinopathy identification.</p>

Classification of Stages Diabetic Retinopathy Using MobileNetV2 Model

Diabetic retinopathy (DR) is a complication of diabetes mellitus that causes retinal damage that can lead to vision loss if not detected and treated promptly. The common diagnosis stages of the disease take time, effort, and cost and can be misdiagnosed. In the recent period with the explosion of artificial intelligence, deep learning has become the most popular tool with high performance in many fields, especially in the analysis and classification of medical images. The Convolutional Neural Network (CNN) is more widely used as a deep learning method in medical imaging analysis with highly effective. In this paper, the five-stage image of modern DR (healthy, mild, moderate, severe, and proliferative) can be detected and classified using the deep learning technique. After cross-validation training and testing on the corresponding 5,590-image dataset, a pre-MobileNetV2 training model is proposed in classifying stages of diabetic retinopathy. The average accuracy of the model achieved was 93.89% with the precision of 94.00%, recall 92.00% and f1-score 90.00%. The corresponding thermal image is also given to help experts for evaluating the influence of the retina in each different stage.