Multilevel Augmentation for Identifying Thin Vessels in Diabetic Retinopathy Using UNET Model
作者机构:Faculty of Computer Science and EngineeringSathyabama Institute of Science and TechnologyChennai600119India Department of Computer Science and EngineeringSt.Joseph’s Institute of TechnologyChennai600119India
出 版 物:《Intelligent Automation & Soft Computing》 (智能自动化与软计算(英文))
年 卷 期:2023年第35卷第2期
页 面:2273-2288页
核心收录:
学科分类:1002[医学-临床医学] 100201[医学-内科学(含:心血管病、血液病、呼吸系病、消化系病、内分泌与代谢病、肾病、风湿病、传染病)] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术(可授工学、理学学位)] 10[医学]
主 题:Image segmentation diabetic retinopathy image augmentation semantic segmentation CNN
摘 要:Diabetic Retinopathy is a disease,which happens due to abnormal growth of blood vessels that causes spots on the vision and vision *** techniques are applied to identify the disease in the early stage with different methods and *** Learning(ML)techniques are used for analyz-ing the images andfinding out the location of the *** restriction of the ML is a dataset size,which is used for model *** problem has been overcome by using an augmentation method by generating larger datasets with multidimensional *** models are using only one augmentation tech-nique,which produces limited features of dataset and also lacks in the association of those data during DR detection,so multilevel augmentation is proposed for *** proposed method performs in two phases namely integrated aug-mentation model and dataset correlation(***).It eliminates overfit-ting problem by considering relevant *** method is used for solving the Diabetic Retinopathy problem with a thin vessel identification using the UNET *** based image segmentation achieves 98.3%accuracy when com-pared to RV-GAN and different UNET models with high detection rate.