Designing and developing automated systems to detect and grade Diabetic Retinopathy (DR) is one of the recent research areas in the world of medical image applications since it is considered one of the main causes of total blindness for people who have diabetes in the mid-age. In this paper, a complete pipeline for retinal fundus images processing and analysis has been described, implemented and evaluated. This pipeline has three main stages: (i) image pre-processing, (ii) features extraction and (iii) classification. In the first stage, the image has been preprocessed using different transformations to standardize the images and to enhance the images quality. It has been

Extreme Learning Machine (ELM) is a well‐known algorithm for the training of neural networks for two modes of functionality: regression and classification. This paper presents a novel model using ELM in ciphering. The study begins with an investigation of the Real‐time Recurrent Neural Network (RRNN) derived from the gradient‐based learning for symmetric cipher. The weakness of this cipher is that the error converges to zero, and that the RRNN will not change regardless of how the plaintext is changed. Given the nature of the ELM, a technique with an ELM‐based cipher is proposed to provide the capability of performing the training independently from the input and the error gradient. Different simulation scenarios were used to evaluate and validate the effectiveness of the proposed cipher. Results revealed that the ELM‐based cipher performed better than RRNNs, especially in terms of security. Moreover, the ELM‐based cipher demonstrated significantly competing performance for a wide range of evaluation measures. Using an ELM‐based cipher instead of an AES or other type of ciphers has the added advantage of providing an addition level of security—by allowing the user to change the algorithmic core of the cipher by simply changing the weights of the neural network. This allows hardware programmed ciphers to be more secure while costing less compared to other ciphers. Copyright © 2016 John Wiley & Sons, Ltd.

No abstract

Nowadays, artificial intelligence applications invade all of the fields including medical applications field. Deep learning, a subfield of artificial intelligence, in particular, Convolutional Neural Networks (CNN), have quickly become the first choice for processing and analyzing medical images due to its performance and effectiveness. Diabetic retinopathy is a vision loss disease that infects people with diabetes. This disease damages the blood vessels in the retina, hence, leads to blindness. Due to the sensitivity and complications involved in managing diabetics, designing and developing automated systems to detect and grade diabetic retinopathy is considered one of the recent research areas in the world of medical image applications. In this paper, the aspects of deep learning field related to diabetic retinopathy have been discussed. Various concepts in deep learning including traditional Artificial Neural Network (ANN) algorithm, ANN drawbacks in context of computer vision and image processing applications, and the best algorithm to overcome ANN drawbacks, CNN, have been elucidated along with the architecture. The paper also reviews an extensive summary of some works in the current research trend and future applications of the DL algorithms in medical image analysis for DR detection and grading. Furthermore, various research gabs related to building such automated systems for medical image analysis have been conferred – such as imbalance dataset which is considered one of the main performance issues that should be handled, the need of high performance computational resources to train deep and efficient models and others. This is quite beneficial for researchers working in the domain of medical image analysis to handle DR.