A Multilevel Deep Feature Selection Framework for Diabetic Retinopathy Image Classification
作者机构：Department of ECECOMSATS University IslamabadWah Campus47040Pakistan Department of Computer Science and EngineeringSoonchunhyang UniversityAsanKorea Department of Electrical EngineeringNUMLRawalpindiPakistan Department of Computer ScienceHITEC University TaxilaTaxilaPakistan
出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)
年 卷 期：2022年第70卷第2期
页 面：2261-2276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)] 10[医学]
主 题：Deep neural network diabetic retinopathy retina features extraction classification
摘 要：Diabetes or Diabetes Mellitus(DM)is the upset that happens due to high glucose level within the *** the passage of time,this polygenic disease creates eye deficiency referred to as Diabetic Retinopathy(DR)which can cause a major loss of *** symptoms typically originate within the retinal space square in the form of enlarged veins,liquid dribble,exudates,haemorrhages and small scale *** current therapeutic science,pictures are the key device for an exact finding of patients’***,an assessment of new medicinal symbolisms stays ***,Computer Vision(CV)with deep neural networks can train models with high *** thought behind this paper is to propose a computerized learning model to distinguish the key precursors of Dimensionality Reduction(DR).The proposed deep learning framework utilizes the strength of selected models(VGG and Inception V3)by fusing the extracated *** select the most discriminant features from a pool of features,an entropy concept is employed before the classification *** deep learning models are fit for measuring the highlights as veins,liquid dribble,exudates,haemorrhages and miniaturized scale aneurysms into various *** model will ascertain the loads,which give the seriousness level of the patient’s *** model will be useful to distinguish the correct class of seriousness of diabetic retinopathy pictures.
维普期刊数据库