INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
ARTIFICIAL INTELLIGENCE BASED GLAUCOMA DETECTION USING MACHINE LEARNING APPROACH
Authors Name:
Priyanka .C
, Pooja. S
Unique Id:
IJSDR2302159
Published In:
Volume 8 Issue 2, February-2023
Abstract:
One of the ophthalmological conditions that commonly results in visual loss in today's culture is glaucoma. There is currently no test that has adequate sensitivity and specificity to diagnose glaucoma on its own. However, previous research have evaluated whether anatomical characteristics of the optic nerve can be predictive of glaucomatous damage. This study offers a public dataset containing health information and fundus photos of the same patient's both eyes. Additionally supplied are segmentations of the cup and optic disc as well as patient labelling based on the analysis of clinical data. A neural network was tested on the dataset to distinguish between healthy people and people with glaucoma. In particular, the ResNet-50 has been utilised as the foundation to categorise patients using data from each eye separately as well as utilising the combined data from each patient's two eyes. In order to advance research on the early diagnosis of glaucoma based on the combined examination of both eyes of the same patient, the results give the baseline measurements.
"ARTIFICIAL INTELLIGENCE BASED GLAUCOMA DETECTION USING MACHINE LEARNING APPROACH", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 2, page no.921 - 928, February-2023, Available :http://www.ijsdr.org/papers/IJSDR2302159.pdf
Downloads:
000337075
Publication Details:
Published Paper ID: IJSDR2302159
Registration ID:204139
Published In: Volume 8 Issue 2, February-2023
DOI (Digital Object Identifier):
Page No: 921 - 928
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn