Scribd
Upload
6 views9 pages

PROPOSAL

Uploaded by

P.Padmini Rani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
6 views9 pages

PROPOSAL

Uploaded by

P.Padmini Rani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

A RESEARCH PROPOSAL ON

EARLY DETECTION OF GLAUCOMA


FROM FUNDUS IMAGES USING
DEEP LEARNING

Presented By
PADMINI RANI.PASUPULETI
CONTENTS

• TITLE
• Objective of the proposal
• Background/short description
• Expected results
TITLE
EARLY DETECTION OF GLAUCOMA FROM
FUNDUS IMAGES USING DEEP LEARNING
OBJECTIVE OF THE PROPOSAL

 The aim of this proposal is to develop an automated diagnostic


technology for early detection of Glaucoma.
 Glaucoma is the problem for long-standing diabetes and the major cause
for visual loss is because of Increased Intraocular Pressure (IOP) of the
fluid in the eye and second leading cause of blindness in the world.
 To observe the features of glaucoma, experts use several imaging
modalities, including confocal scanning laser ophthalmoscopy (CSLO),
Heidelberg retina tomography (HRT), optical coherence tomography
(OCT) techniques for detecting Glaucoma is very expensive.
 To early detection of Glaucoma, so that the ophthalmologist advises the
patient easily and It is applicable for any fundus image of Human being.
BACKGROUND/SHORT DESCRIPTION
Glaucoma is one of the severe visual diseases that lead to damage the eyes
irreversibly by affecting the optic nerve fibers and astrocytes. Consequently, the
early detection of glaucoma plays a virtual role in the medical field. The literature
presents various techniques for the early detection of glaucoma. Among the
various techniques, retinal image-based detection plays a major role as it comes
under non-invasive methods of detection. While detecting glaucoma disorder
using retinal images, various medical features of the eyes, such as retinal nerve
fiber layer, cup-to-disc ratio, apex point, optic disc, and optic nerve head, and
image features are used. The detection of Glaucoma manually is expensive and
time taken. As performing retinal screening examinations is a time taken and
unmet need on all patients, automated medical image analysis helps in identifying
the disease severity.
• Research is going on Glaucoma in various agencies and some existing
methodologies gave good results for small size of datasets using traditional
methods. But I will be worked on large datasets using deep learning
techniques to detect Glaucoma early stage. My aim is to detect Glaucoma
from fundus images using deep learning models in very effectively and
efficiently with new proposed algorithm.
• A data set was taken from Kaggle and it was preprocessed. Differenet
machine learning techniques are applied on the dataset which we taken. the
following are the accuracies obtained.

ALGORITHM ACCURACY

KNN 73

SVM 75

ADABOOST CLASSIFIER 78
EXPECTED RESULTS
As Glaucoma is eventually been found in IOP is increased rapidly, its detection through
manually is a time taken process. As the prevention of Glaucoma is a challenge for
ophthalmologists, to overcome this drawback and to detect Glaucoma in a very less time an
early detection of Glaucoma using deep learning is proposed in this study. This model will be
helpful for ophthalmologists in detecting Glaucoma within a less span of time.
THANK YOU

You might also like