Diabetes Retinopathy is a disease which results from a prolonged case of diabetes mellitus and it is the most common cause of loss of vision in man. Data mining algorithms are used in medical and computer fields to find effective ways of forecasting a particular disease. This research was aimed at determining the effect of using feature selection in predicting Diabetes Retinopathy. The dataset used for this study was gotten from diabetes retinopathy Debrecen dataset from the University of California in a form suitable for mining. Feature selection was executed on diabetes retinopathy data then the Implementation of k-Nearest Neighbour, C4.5 decision tree, Multi-layer Perceptron (MLP) and Support Vector Machines was conducted on diabetes retinopathy data with and without feature selection. There was access to the algorithms in terms of accuracy and sensitivity. It is observed from the results that, making use of feature selection on algorithms increases the accuracy as well as the sensitivity of the algorithms considered and it is mostly reflected in the support vector machine algorithm. Making use of feature selection for classification also increases the time taken for the prediction of diabetes retinopathy.
Security and privacy of patients' information remains a major issue of concern among health practitioners. Therefore, measures must be put in place to ensure that unauthorized individual do not have access to this information. However, the adoption of digital alternative of retrieving and documenting medical information has further opened it up to more attacks. This article presents a modified blowfish algorithm for securing textual and graphical medical information. The F-function used in generating round sub-keys was strengthened so as to produce a strong key that could resist differential attacks. Number of Pixel Change Rate (NPCR) and Unified Average Changing Intensity (UACI) of 98.85% and 33.65% revealed that the modified algorithm is sensitive to changes in its key and also resistive to differential attacks. Furthermore, the modified algorithm demonstrated a better encryption and decryption time than the existing blowfish algorithm.
Over the last decades, various methods have been employed in medical images analysis. Some state-of-the-arts techniques such as deep learning have been recently applied to medical images analysis. This research proposes the application of deep learning technique in performing segmentation of retinal blood vessels. Analyzing and segmentation of retina vessels has assisted in diagnosis and monitoring of some diseases. Diseases such as age-related fovea degeneration, diabetic retinopathy, glaucoma, hypertension, arteriosclerosis and choroidal neovascularization can be effectively managed by the analysis of retinal vessels images. In this work, a Deep Convolutional Encoder-Decoder Architecture for the segmentation of retinal vessels images is proposed. The proposed method is a deep learning system composed of an encoder and decoder mechanism allows a low resolution image set of retinal vessels to be analyzed by set of convolutional layers in the encoder unit before been sent into a decoder unit for final segmented output. The proposed system was evaluated using some evaluation metrics such as dice coefficient, jaccard index and mean of intersection. The review of the existing works was also carried out. It could be shown that the proposed system outperforms many existing methods in the segmentation of retinal vessels images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.