A deep learning framework for early detection of glaucoma in Retinal fundus images

Abstract

In the field of biomedical engineering, the identification of newlinephysiological changes inside the human body is a challenging task. At present, newlineidentifying these abnormalities is graded manually which is very difficult, newlinetime-consuming, and tedious as it includes several complicated procedures. newlineHence, the use of Computer-Aided Diagnosis (CAD) gained more attention newlinedue to the necessity of a diseases detection system at an early stage. The newlineprimary focus of this research is to develop a CAD system for early detection newlineand to aid the screening and management of glaucoma. newlineGlaucoma is another leading cause of blindness worldwide and newlineranks third in India, which affects the peripheral vision. Since, the damage newlinecaused is irreversible and early detection of glaucoma is significant for newlinepreventing eye disease from getting severe, mass screening would be the only newlineoption for early detection among the immense population for predicting the newlineseverity of glaucoma. Fundus camera is the cheapest imaging analysis newlinemodality which suits the monetary demands of the population. The newlinecharacterization of glaucoma can be done by extracting structural features from newlinethe segmented optic disc and optic cup. newlineThe main objective of this research is to predict the potentiality newlineof the image analysis model for early detection and diagnosis of glaucoma for newlineassessing ocular pathologies. The proposed CAD system would assist the newlineophthalmologist in diagnosing ocular diseases by proving a second opinion as newlinehuman expert s decision. The three approaches investigated in this research newlinework are summarized below: newline