Diabetic Retinopathy with exudates causes a major problem in human visualization and becomes a cause of blindness to diabetic patients. In addition, the numbers of diabetic retinopathy patients are increasing while the numbers of doctors are not easily increased in the same proportion. This circumstance causes a heavy work load for doctors. In the past, the medical image processing research has shown that simply getting a second opinion can significantly help physician's diagnosis. This research proposes a method to detect exudates from diabetic retinopathy images. The early exudates detection of diabetic retinopathy patients will reduce seriousness in diabetic retinopathy. The proposed method for detecting exudates consists of 5 major steps as follows:
1) To improve the quality of images by using the contrast limited adaptive histogram equalization (CLAHE) 2) To apply the object attribute thresholding algorithm (OAT) for non-retinal object removal, 3) To implement Frangi's algorithm based on Hessian filtering for blood vessel detection 4) To detect the retinal optic disc by applying the combination between multi-resolution analysis and Hough transform and 5) To classify exudates in the remaining region with algorithms of hierarchical fuzzy-c-meanclustering. The performance of the proposed method is evaluated on DIARETDB, which is the retinal image database of the Lappeenranta University of Technology, where the performance is good enough for exudates detection.
Risk factors for Type 2 diabetes is very important for developing diabetes prediction tools instead of blood testing. Recently, many researches have studied risk factors of diabetes in order to apply them to be a tool for diabetes prediction by using Logistic Regression (LR), Radial Basis and Back-propagation Neural Network (BNN). However, the accuracy is not higher. This paper presents new factors that are smoking and alcohol consumption to improve accuracy in diabetes prediction. Some traditional factors i.e., body mass index (BMI), blood pressure (BP) and waist circumference (WC) and Family History (FMH) are also proposed to extent by adjusting and additional range. The proposed diabetes prediction method is based on BNN. Approximately 2,000 cases of Thai people at BMC hospital, Thailand during 2010 to 2012 are used to train the BNN. From experiment results, each proposed factors i.e., FMH, Alcohol consumption factor, Smoking Factors and WC gives a value of accuracy that is higher than baseline as 83.35%, 83.5%, 83.6% and 83.65%, respectively. After that, this paper focuses on tuning neural network parameter, which is divided into 3 main steps: number of hidden nodes, sequence of integrating the proposed factors, and other parameter i.e., learning rate, and Iteration. Finally, the proposed factors and tuning BNN parameters introduce a high accuracy compared with the baseline up to 1.2%.
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.