Beta
ManageSearchChatDiscover
166333

Neural Networks Applied to Grading of Cup-Disk Ratio in Glaucomatous Cases.

Article

Last updated: 22 Jan 2023

OverviewSimilar Items

Subjects

-

Tags

Electrical Engineering

Abstract

Automatic measurement of cup-disc ratio is a challenging problem. This problem could be efficiently solved with a neural network based learning technique. The eye signature renders the measurement of this ratio a tedious task. The physicians prepared maps for grading of this ratio. These maps classify the development of disease in a human eye in nine stages as shown in Figure 1. Neural networks and their solution time is very strongly dependent upon the initial random values of the synaptic connections and the order of pattern presentation to the input layer. Therefore it was necessary to study this phenomena and experiment with different distributions and show their effect on the speed of convergence. A multilayer neural network is designed and trained with the back propagation technique to assign an eye signature to its corresponding ratio. This helps the physician in the diagnosis of glaucoma. The automatic grading of cup-disc ratio offers the advantage of objective grading over thevisual inspection. 

DOI

10.21608/bfemu.2021.166333

Authors

First Name

A.

Last Name

Tolba

MiddleName

-

Affiliation

Electrical Engineering Department., Suez Canal University.

Email

-

City

Mansoura

Orcid

-

First Name

S.

Last Name

Sitteen

MiddleName

A.

Affiliation

Ophthalmology Department., El-Mansoura University.,Mansoura., Egypt.

Email

-

City

Mansoura

Orcid

-

Volume

18

Article Issue

4

Related Issue

24036

Issue Date

1993-12-01

Receive Date

1993-10-11

Publish Date

2021-12-01

Page Start

39

Page End

48

Print ISSN

1110-0923

Online ISSN

2735-4202

Article File

BFEMU_Volume 18_Issue 4_Pages 39-48.pdf

PDF . 313.6kB

Link

https://bfemu.journals.ekb.eg/article_166333.html

Detail API

https://bfemu.journals.ekb.eg/service?article_code=166333

Order

7

Type

Research Studies

Type Code

1,205

Publication Type

Journal

Publication Title

MEJ. Mansoura Engineering Journal

Publication Link

https://bfemu.journals.ekb.eg/

MainTitle

-

Details

Type

Article

Created At

22 Jan 2023