Department of Electronics and Communication Engineering
Academic Year (2019-2023)
FIRST PROJECT REVIEW
DETECTION OF DIABETIC
RETINOPATHY USING DEEP LEARNING
Guided By: Presented by,
D r. J . P r a d e e p , Rajesh P (19TC0172)
Associate professor Jagadeesan A (19TC0109)
ECE Department Yokesh S (19TC0253) -
19TC0200
AGENDA
OBJECTIVE
LITERATURE SURVEY
PROBLEM DEFINITION
INTRODUCTION
PROJECT METHODOLOGY
ALGORITHM
BLOCK DIAGRAM
SO FOR WORK DONE..
REFERENCES
OBJECTIVE
•To detect the early of diagnosis of Diabetic Retinopathy using Deep Learning
techniques.
LITERATURE SURVEY
I. Kele Xu et al., [6] has developed an approach to DR detection using deep CNN. In this work,
the authors used the publicly available data set Kaggle. Data augmentation Steps are used such
as stretching, translation, flipping, And rotate to the labeled dataset. CNN’s architecture is then
used for automatic DR classification and achieves 94.5\% accuracy.
II. Vishakha Chandore et al., [7] have evolved a method for automatic disclosure of DR using
deep CNN. A large dataset of around 35000 images is used. In this work, images are resized
into dimensions of 448x448. They also applied various data augmentation steps. and Finally,
the authors achieved a precision for class 0 is 81\% and for class 1 88\%.
III. Dinial Qomariah et al., [9] have suggested a method for the classification of DR and healthy
retinal images using CNN and SVM. They used the publicly accessible Messidor database.
Here features are obtained using transfer learning and accuracy of 95.83\% for base 12 and for
inception v3 and VGG19 95.24\% for base 13 is achieved.
IV. Harry Pratt et al., [10] have developed a model for diagnosis of DR using CNN. Here images are
rescaled into 512x512 pixels. Here the Kaggle dataset is used. In this research, the CNN architecture
can be built to define the dynamic characteristics involved. in the task of classification. They achieved
a Recall of 95\% and 75\% of accuracy.
V. Nidhi Kamothi., [11] have suggested a method for Automatic Diagnosis of DR using Transfer
Learning. Image preprocessing steps are used such as image enhancement and converted in the
desired format. After that various CNN architectures are used like CNN, VGG16, and VGG19. They
reported the accuracy of the model based on the VGG16 is 71.6\%.
PROBLEM DEFINITION
Diabetic retinopathy is a leading cause of vision loss globally.
Of an estimated 285 million people with diabetes mellitus worldwide approximately one third have
signs of DR and of these, a further one third of DR is vision-threatening DR.
As it is a leading disease in the west there needs to be an solution and way to identify the disease.
In order to overcome this problem, proposing to detect the disease in prior and various features
extraction techniques are proposed for extraction of diabetic retinopathy features for early detection .
INTRODUCTION
• Diabetic retinopathy is a diabetes complication that affects
eyes
• According to a World Health Organization survey, the
global incidence of diabetes was 2.8\% in 2000 and by
2030 current statistics will rise by 4.4\%.
• It's caused by damage to the blood vessels of the light-
sensitive tissue at the back of the eye (retina)
• The general signs and symptoms of DR are blurry vision,
floaters and flashes, and loss of vision
PROJECT METHODOLOGY
Different steps involved in methodology are given below:
● Get the Dataset. ● Data Preprocessing.
● The dataset is divided into two parts: training and testing.
● Data augmentation technique used.
● Use CNN algorithm for training the model.
● Get the evaluation matrices.
● Get predictions.
● Make a classification table.
ALGORITHM
SOFTWARE REQUIREMENTS
MATLAB
BLOCK DIAGRAM
SO FOR WORK DONE….
Project Domain – Image Processing (Medical Image Processing )
Project Tittle- DIABETIC RETINOPATHY USING DEEP LEARNING.
Currently studying about the various techniques related to this project.
REFERENCES
1. M. A. Habib Raj, M. A. Mamun and M. F. Faruk, "CNN Based Diabetic Retinopathy
Status Prediction Using Fundus Images," 2020 IEEE Region 10 Symposium
(TENSYMP), 2020, pp. 190-193, doi: 10.1109/TENSYMP50017.2020.9230974.
2. Y. Kumar, N. Poonia and P. Jain, "Detection of Non-proliferative Diabetic Retinopathy
using GUI," 2022 2nd International Conference on Innovative Practices in Technology
and Management (ICIPTM), 2022, pp.
283-286,doi:10.1109/ICIPTM54933.2022.9754212.
3. V. Sudha and D. T. R. Ganeshbabu, ‘‘A convolutional neural network classifier VGG-19
architecture for lesion detection and grading in diabetic retinopathy based on deep
learning,’’ Comput., Mater. Continua, vol. 66, no. 1, pp. 827–842, 2020.
REFERENCES
4. J. Liu, and F. An, "Image Classification Algorithm Based on Deep Learning-Kernel
Function," Scientific Programming, vol. 2020, pp. 1-14, Jan, 2020,
10.1155/2020/7607612.
5. Andrew D, MD, PhD, University of Iowa, Retina, Diabetic Retinopathy, [Link]
Available at - [Link] Accessed on
– 13-10-2020
