Diabetic Retinopathy Classification Using Deep
Learning Techniques to enhance the finding using
color neutralization techniques
Introduction
Diabetic retinopathy (die-uh-BET-ik ret-ih-NOP-uh-thee) is a diabetes complication that affects eyes. It's
caused by damage to the blood vessels of the light-sensitive tissue at the back of the eye (retina). At first,
diabetic retinopathy might cause no symptoms or only mild vision problems. But it can lead to blindness.
The condition can develop in anyone who has type 1 or type 2 diabetes. The longer you have diabetes and
the less controlled your blood sugar is, the more likely you are to develop this eye complication. Diabetic
Retinopathy is regarded as the leading cause of blindness for diabetic patients, especially the working-age
population in developing nations. Treatment involves sustaining the patient's current grade of vision since
the disease is irreversible. Early detection of Diabetic Retinopathy is crucial in order to sustain the
patient's vision effectively. The main issue involved with DR detection is that the manual diagnosis
process is very time, money, and effort consuming and involves an ophthalmologist's examination of eye
retinal fundus images. The latter also proves to be more difficult, particularly in the early stages of the
disease when disease features are less prominent in the images. Machine learning-based medical image
analysis has proven competency in assessing retinal fundus images, and the utilization of deep learning
algorithms has aided the early diagnosis of Diabetic Retinopathy (DR).
Problem Definition
We will propose real time image processing techniques in deep learning methods for image
classifications and detections of rental fundus by using the in supervised, self-supervised types of
machine learning and try to get the maximum accuracy of prediction.
In literature survey, we found that images exists in the dataset are having the quality issues so we
also proposed some image improvement technique in the process such as color normalization to
improve the image quality and gets the better results for Diabetic Retinopathy (DR) detection and
classification.
For instance, referable, non-referable, and proliferative classifications of Diabetic Retinopathy are
reviewed and summarized. Moreover, the project discusses the available retinal fundus datasets
for Diabetic Retinopathy that is used for tasks such as detection, classification, and segmentation.
Aim:
The main aim of the proposed project is to give the alternative automotive system to the medical
eternity to classify and detect the Diabetic Retinopathy (DR) through the advance machine
learning techniques and image processing methods.
The machine learning techniques will improve its capability as we maintain the maximum data in
the training and testing sets this will results in more trust in the system for more faster diagnosis
of disease and immediate medical help to patient.
Objectives
1. Preprocess the sample datasets to evaluate the input images have the symptoms of
the Diabetic Retinopathy or the input image is healthy non diabetic persons retina image.
2. The Input image has the quality to evaluate every detail to identify the Diabetic
Retinopathy. Bad quality images will be omitted from the sample data.
3. We will work for color normalization technique so that we will improve the image
quality so that the detection algorithm gets the best possible inputs for feature extraction.
4. Predict the classification/ stages of Diabetic Retinopathy the deep learning algorithm by
introducing two hidden layers which will increase the accuracy.
5. We want to build an AI based algorithm which will automatically train the dataset for
future work; it will help the project to increase the accuracy of the results.
6. The project also assesses research gaps in the area of DR detection/classification and
addresses various challenges that need further study and investigation.
Literature Review
Paper Title Publication Overview
date
Base Paper Deep Learning Diabetic Retinopathy (DR) is a degenerative
Techniques for 2022 disease that impacts the eyes and is a
Diabetic consequence
Retinopathy of Diabetes mellitus, where high blood glucose
levels induce lesions on the eye retina. Diabetic
Classification: A
Retinopathy
Survey is regarded as the leading cause of blindness for
diabetic patients, especially the working-age
population in developing nations. Treatment
involves sustaining the patient's current grade of
vision since the disease is irreversible. Early
detection of Diabetic Retinopathy is crucial in
order to sustain the patient's vision effectively.
The main issue involved with DR detection is
that the manual diagnosis process is very time,
money, and effort consuming and involves an
ophthalmologist's examination of eye retinal
fundus images. The latter also proves to be more
dif_cult, particularly in the early stages of the
disease when disease features are less prominent
in the images. Machine learning-based medical
image analysis has proven competency in
assessing retinal fundus images, and the
utilization of deep learning algorithms has aided
the early diagnosis of Diabetic Retinopathy
(DR).
Reference 2018
Diabetic The Diabetes Mellitus (DM). In literature
Paper
Retinopathy: various machine learning algorithms have been
Present and Past applied in detection of DR. This involves two
Ankita Guptaa, steps; Feature extraction and Classification. This
Rita Chhikarab paper reviews the various techniques used for
detecting DR based on the features like blood
vessels, microaneurysms, haemorrhages etc. In
most of the experiments retinal fundus images
were used in which images of retina were
captured by fundus camera. This review
bifurcates the detection of DR into two
approaches; Blood vessels segmentation and
Identification of lesions. This paper compares
the experimental results of various machine
learning techniques based on parameters like
sensitivity, specificity, Area Under Curve
(AUC), Accuracy. The results are also compared
with the deep neural networks and analysis of
best technique has been provided.
Reference Diabetic 2020 Diabetic Retinopathy (DR) is a common
Paper retinopathy Complication of diabetes mellitus, which causes
detection through lesions on the retina that effect vision. If it is not
deep learning detected early, it can lead to blindness.
techniques: A Unfortunately, DR is not a reversible process,
review and treatment only sustains vision. DR
Wejdan L. early detection and treatment can significantly
Alyoubi, Wafaa reduce the risk of vision loss. The manual
M. Shalash, diagnosis process of DR retina fundus images by
Maysoon F. ophthalmologists is time-, effort-, and cost-
Abulkhair consuming and prone to misdiagnosis unlike
PII: S2352- computer-aided diagnosis systems. Recently,
9148(20)30206-9 deep learning has become one of the most
common techniques that has achieved better
performance in many areas, especially in
medical image analysis and classification.
Convolutional neural networks are more widely
used as a deep learning method in medical image
analysis and they are highly effective. For this
article, the recent state-of-theart methods of DR
color fundus images detection and classification
using deep learning techniques have been
reviewed and analyzed. Furthermore, the DR
available datasets for the color fundus retina
have been reviewed. Difference challenging
issues that require more investigation are also
discussed.
Reference 2022
Paper Diabetic Diabetic Retinopathy is a condition which
Retinopathy occurs most commonly in patient with type 1 or
Detection using type 2 diabetes. It affects the blood vessels of
Pre-trained eye and delay in treatment can cause loss of
EfficientNetB3 vision. With the current state of the art deep
Model learning technology, image classification can be
performed with an accuracy as high as that of a
human being. The idea behind this paper was to
develop a highly accurate and reliable multi-
class deep learning model which can detect the
class of severity of diabetic retinopathy in a
patient given an image of retinal fundus. The
Aptos 2019 dataset was used for training the
deep learning model. The proposed model also
considered the high class-imbalance in the used
dataset.
Results – Our model achieved 99.18%
categorical accuracy in training set and 75.68%
categorical accuracy in validation set.
Methodology
Data preprocessing
Data preprocessing is necessary to prepare the d iabetic retinopathy dataset images in to its
classifications in a manner that a deep learning model can accept. Separating the training and
testing datasets ensures that the model learns only from the training data and tests its
performance with the testing data. The dataset was divided into training and test data.
Building and training model
The construction of a deep learning model includes three types of layers.
1. The input layer is the layer to which the features of datasets will be passed. There is no
computation that occurs in this layer. It serves to pass features to the hidden layers.
2. The hidden layers are the layers between the input layer and the output layer.
There can be various numbers of hidden layers. These layers Perform the computations
and pass the information to the output layer at the end.
3. The output layer represents the layer of our neural network. It will give the results after
training a new created model. It is responsible for producing the output variables.
Visualizing loss and accuracy
Visualization of the performance of any deep learning model is an easy way to make sense of the
data being output by the model and make an informed decision about the changes that need to be
made on the parameters or hyper parameters that affect the deep learning model From the
accuracy plot, the model might achieved high training accuracy on both datasets. We have to also
see that the model has not yet over learned the training dataset, showing comparable results for
both datasets.
References
1. Attia, Z. Akhtar, S. Akrouf, and S. Maza, ``A survey on machine and deep learning for
detection of diabetic RetinopathY,'' ICTACT J. ImageVideo Process., vol. 11, no. 2, pp.
2337_2344, Dec. 2020.
2. A. Gupta and R. Chhikara, ``Diabetic retinopathy: Present and past,'' Proc.Comput. Sci.,
vol. 132, pp. 1432_1440, Jan. 2018.
3. W. L. Alyoubi,W. M. Shalash, and M. F. Abulkhair, ``Diabetic retinopathy detection
through deep learning techniques: A review,'' Informat. Med.Unlocked, vol. 20, Jan.
2020, Art. no. 100377.
4. S. Stolte and R. Fang, ``A survey on medical image analysis in diabetic retinopathy,''
Med. Image Anal., vol. 64, Aug. 2020, Art. no. 101742.
5. N. Asiri, M. Hussain, F. Al Adel, and N. Alzaidi, ``Deep learning based computer-aided
diagnosis systems for diabetic retinopathy: A survey,'' 2018, arXiv:1811.01238.
6. S. Valarmathi and R. Vijayabhanu, ``A survey on diabetic retinopathy disease detection
and classi_cation using deep learning techniques,'' in Proc. 7th Int. Conf. Bio Signals,
Images, Instrum. (ICBSII), Mar. 2021, pp. 1_4.
7. Shamshad, S. Khan, S. W. Zamir, M. H. Khan, M. Hayat, F. S. Khan, and H. Fu,
``Transformers in medical imaging: A survey,'' 2022, arXiv:2201.09873.
