DR Synopsis

INTRODUCTION
Diabetes is a disease that has a major prevalence in our population. One of the complications
resulting from the disease is diabetic retinopathy (DR).
A commonly used method of diagnosing DR is by analysing fundus images of the eye and
classifying the condition, if present, into one of the following categories: Mild, Moderate or
severe non-proliferative diabetic retinopathy and proliferative diabetic retinopathy.
Usually, an ophthalmologist analyzes their images and makes a diagnosis based on knowledge
gained from the previous studies. With the increasing capability of artificial intelligence, more
specifically, Convolutional Neural Networks (CNNs), this processes of identifying and
deciding if fundus scans are indicative of diabetic retinopathy, can be tasked to such a network.
There have been mini studies that have aimed to determine whether or not fundus images
showed signs of diabetic retinopathy using computer vision. Some take the extra step to classify
DR indicative images into one of the previously mentioned categories.
The aim of this study is to use this technology along with a library of classified DR images to
first, train a CNN to recognise diabetic and non-diabetic images and secondly, visualize the
trained CNN, to search for any new indicators of DR that may not have been used by physicians
before to diagnose the disease. These factors may help in increasing the accuracy of diagnose
and allowing detection at an earlier stage.
Fig a. Normal Retina Fig b. Infected Retina

LITERATURE SURVEY
SL.NO Reference Technology Limitations
Used
1 Gulshan et al (2015) Deep Limited to
Development and Validation of a Deep Learning Convolutional fundus
Algorithm for Detection of Diabetic Retinopathy in Neural photographs;
Retinal Fundus Photographs Networks generalization
https://research.google.com/pubs/archive/45732.pdf (CNN) to other
imaging
modalities is
challenging.
2 Ting et al (2017) Deep neural Emphasis on
Development and Validation of a Deep Learning System network with a diabetic
for Diabetic Retinopathy and Related Eye Diseases Using diverse dataset populations
Retinal Images From Multi ethnic Populations With may limit
Diabetes applicability to
https://pubmed.ncbi.nlm.nih.gov/29234807/ non-diabetic
retinopathy
cases.
3 Rajalakshmi et al (2018) Comparative Lack of
Deep learning vs traditional computer-aided detection and analysis of standardization
diagnosis of retinal diseases: a review deep learning in datasets and
https://www.nature.com/articles/s41433-018-0064-9 and traditional evaluation
methods metrics;
potential bias in
comparison.
4 Abramoff et al (2018) Automated AI Dependency on
Pivotal Trial of an Autonomous AI-Based Diagnostic system for primary care
System for Detection of Diabetic Retinopathy in Primary primary care settings; may
Care Offices not replace
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6550188/ specialized
diagnosis in all
cases.
5 Ting et al (2020) Comprehensive General
Artificial Intelligence and Deep Learning in review of AI challenges in
Ophthalmology and deep AI applications,
https://pubmed.ncbi.nlm.nih.gov/30361278/ learning in such as
ophthalmology interpretability
and ethical
concerns.
6 Bellemo et al (2021) Real-world External factors
Artificial intelligence – supported diabetic retinopathy implementation affecting real-
screening; a real – world, multicentre of AI- world
https://link.springer.com/article/10.1007/s40123-023- supported implementation,
00691-3 screening including
variations in
image quality
and data
privacy issues.
PROBLEM STATEMENT
Diabetic retinopathy is a common complication of diabetes, affecting the eyes and
potentially leading to blindness if not managed effectively. Many individuals with
diabetes, particularly in undeserved populations, lack access to timely and effective
screening, diagnosis, and treatment for diabetic retinopathy. The problem statement
revolves around the need to improve screening and diagnostic methods, increase access
to eye care services, and raise awareness and education regarding regular eye exams for
individuals with diabetes.
OBJECTIVES
• Concern Doctors related to disease.

• Symptoms and Treatments.
• To identify and decide Diabetic Retinopathy (DR) using digital fundus images.
• Identifying the severity of Diabetic Retinopathy (DR).
• Prevent blindness
• Detect the condition early
• 7.To determine the actual positions and dimensions of the spots
EXPECTED OUTCOMES
• Describe the epidemiology of Diabetic Retinopathy (DR).

• Correlate the pathogenesis of Diabetic Retinopathy (DR) with clinical presentation.
• Identify signs of proliferative Diabetic Retinopathy (DR) and high risk Non-
Proliferative Diabetic Retinopathy (DR) on a given fundus photography.
• Outline the management for Diabetic Retinopathy (DR).

DR Synopsis

Uploaded by

Copyright:

Available Formats

DR Synopsis

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

DR Synopsis

Uploaded by

Copyright:

Available Formats

INTRODUCTION

Fig a. Normal Retina Fig b. Infected Retina

• Concern Doctors related to disease.

• Describe the epidemiology of Diabetic Retinopathy (DR).

You might also like