Detection of Hypertension Retinopathy Using Deep Learning and Boltzmann Machines

International Conference on Computing and Applied Informatics 2016

物理学;计算机科学

Triwijoyo, B.K.^1 ; Pradipto, Y.D.^2

Doctor of Computer Science, BINUS University Jakarta, Indonesia^1

Psychology Department, Faculty of Humanities, BINUS University Jakarta, Indonesia^2

关键词: Boltzmann machines;    Combined features;    Cotton-wool spots;    Early diagnosis;    High blood pressures;    Image pattern recognition;    Process of learning;    Prototype system;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/801/1/012039/pdf
DOI  :  10.1088/1742-6596/801/1/012039

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

hypertensive retinopathy (HR) in the retina of the eye is disturbance caused by high blood pressure disease, where there is a systemic change of arterial in the blood vessels of the retina. Most heart attacks occur in patients caused by high blood pressure symptoms of undiagnosed. Hypertensive retinopathy Symptoms such as arteriolar narrowing, retinal haemorrhage and cotton wool spots. Based on this reasons, the early diagnosis of the symptoms of hypertensive retinopathy is very urgent to aim the prevention and treatment more accurate. This research aims to develop a system for early detection of hypertension retinopathy stage. The proposed method is to determine the combined features artery and vein diameter ratio (AVR) as well as changes position with Optic Disk (OD) in retinal images to review the classification of hypertensive retinopathy using Deep Neural Networks (DNN) and Boltzmann Machines approach. We choose this approach of because based on previous research DNN models were more accurate in the image pattern recognition, whereas Boltzmann machines selected because It requires speedy iteration in the process of learning neural network. The expected results from this research are designed a prototype system early detection of hypertensive retinopathy stage and analysed the effectiveness and accuracy of the proposed methods.