The current issue and full text archive of this journal is available on Emerald Insight at:

[Link]

Using transfer learning for diabetic Classifying

diabetic
retinopathy stage classification retinopathy
stage
Enas M.F. El Houby
Department of Systems and Information, Engineering Division,
National Research Centre, Giza, Egypt
Received 15 July 2021
Abstract Revised 27 August 2021
Purpose – Diabetic retinopathy (DR) is one of the dangerous complications of diabetes. Its grade level must be Accepted 13 September 2021
tracked to manage its progress and to start the appropriate decision for treatment in time. Effective automated
methods for the detection of DR and the classification of its severity stage are necessary to reduce the burden on
ophthalmologists and diagnostic contradictions among manual readers.
Design/methodology/approach – In this research, convolutional neural network (CNN) was used based on
colored retinal fundus images for the detection of DR and classification of its stages. CNN can recognize
sophisticated features on the retina and provides an automatic diagnosis. The pre-trained VGG-16 CNN model
was applied using a transfer learning (TL) approach to utilize the already learned parameters in the detection.
Findings – By conducting different experiments set up with different severity groupings, the achieved results
are promising. The best-achieved accuracies for 2-class, 3-class, 4-class and 5-class classifications are 86.5, 80.5,
63.5 and 73.7, respectively.
Originality/value – In this research, VGG-16 was used to detect and classify DR stages using the TL
approach. Different combinations of classes were used in the classification of DR severity stages to illustrate
the ability of the model to differentiate between the classes and verify the effect of these changes on the
performance of the model.
Keywords Deep learning, Diabetic retinopathy, Retinal fundus images, Transfer learning
Paper type Research paper

1. Introduction
Diabetes mellitus is a chronic disease that is caused by the inability of the pancreas to produce
a sufficient amount of insulin, which is a hormone that adjusts blood sugar, or it is the
inability of the body to use the produced insulin effectively. High blood sugar is a prevalent
result of uncontrolled diabetes and eventually affects many systems of the body, such as
blood vessels and nerves. Therefore, it is a main cause of blindness, heart attacks, strokes and
kidney failures [1]. Diabetic retinopathy (DR) is considered one of the serious complications of
diabetes, which is responsible for 2.6% of overall blindness. High levels of blood sugar
destroy the blood vessels in the retina. That rises the probability of fluid leakage and bleeding
which results in dangerous vision problems that might leads to blindness [2]. To decrease the
dangerous effect of DR, early detection, precise diagnosis and appropriate treatment are
required [3, 4]. Therefore, an intelligent automated method for early and accurate detection of
DR is required to manage the progress of the disease and thus guarantee appropriate
treatment.
Classification of DR includes the weighting of many features and finding the position of
these features. This is an exhausting time-consuming task for ophthalmologists, and it is

© Enas M.F. El Houby. Published in Applied Computing and Informatics. Published by Emerald
Publishing Limited. This article is published under the Creative Commons Attribution (CC BY 4.0)
licence. Anyone may reproduce, distribute, translate and create derivative works of this article (for both
commercial and non-commercial purposes), subject to full attribution to the original publication and Applied Computing and
Informatics
authors. The full terms of this licence may be seen at [Link] Emerald Publishing Limited
legalcode e-ISSN: 2210-8327
p-ISSN: 2634-1964
Conflict of interest: The authors have no conflict of interests to declare. DOI 10.1108/ACI-07-2021-0191
ACI prone to mistakes. Therefore, ophthalmologists can be supported by computer aided
diagnosis systems, which can detect abnormalities and classify the severity of different cases.
They can decrease the load on ophthalmologists and reduce inconsistencies between manual
readers. Great work is achieved on detecting DR automatically using tradition methods such
as k-nearest neighbor (K-NN) and support vector machine (SVM) that depend on hand-crafted
features extraction and then classifying different cases depending on the selected features
[5, 6]. In contrast, features can be learned automatically from the original images through the
training phase using deep learning [7].
The advancement in deep learning has motivated researchers to use deep learning in
medical images analysis. Convolutional neural network (CNN) is a type of deep learning
networks that are specialized in applications of image analysis. Where the layers nearer to the
input of the model learn low-level features like lines, the layers in the middle learn convoluted
abstract features that integrate the lower level features, and the layers closer to the output
interpret the features extracted in the context of the classification [8]. The high-performing
CNN models that were recently applied in image classification tasks and achieved high
performance can be imported and used for another image classification task using transfer
learning (TL) approach.
TL approach is to utilize a pre-trained model to train a new model. It uses the knowledge
obtained during solving one problem and exploits it in solving various but relevant problems.
The traits learned by pre-training on the large dataset can be transferred to the new network,
where only the classification component is trained on the new smaller dataset, to fine-tune the
new data. TL saves considerable time used in developing and training a deep CNN model [9].
There are many high-performing pre-trained models that can be imported and used for image
recognition. Most of these models have been developed as part of the annual ImageNet Large
Scale Visual Recognition Challenge (ILSVRC). Examples of these models from the published
literature are visual geometry group (VGG) [10], inception modules (GoogleNet) [11, 12],
residual neural network (ResNet) [13] and neural architecture search network (NasNetLarge)
[14] etc. These models were trained using ImageNet data which consists of 1,000,000 images
with 1,000 classes, so they have learned to detect generic features and their learned weights
are provided and used in similar problems. They achieved state-of-the-art performance and
when used to develop other image recognition tasks, they remain effective [15, 16].
In this research, a TL approach using a per-trained model VGG-16 was utilized to detect
DR and classify its stages based on retinal fundus images. The remainder of the paper is
organized as follows; related research articles about the detection and diagnosis of DR are
reviewed in section 2. The proposed method for detection and classification of DR is
introduced in section 3. The experimental results of the proposed model are illustrated in
section 4. The discussion and comparison with the literature are presented in section 5.
Finally, conclusion and future work are drawn in section 6.

2. Related work
Many systems were proposed in the literature for the detection and diagnosis of DR using
various machine learning techniques (MLTs). These systems are either based on
conventional MLTs, which depend on hand-crafted features extraction, or deep learning
where the features are extracted automatically during the training. In the next sections, some
of these systems that were found in the literature will be illustrated.
Based on conventional MLTs, random forest (RF) was used to classify fundus images
according to DR grades based on 35 extracted features from the detected red lesions and
achieved an accuracy of 74.1% on Messidor dataset [17]. Three classifiers which are neural
network, RF and SVM were applied on the DIAbetic RETinopathy DataBase fundus images
to classify microaneurysms which are early indicators of DR, based on collected patches from
images. An AUC of 0.985 and F-measure of 0.926 were achieved using SVM classifier which Classifying
outperformed the other classifiers [18]. The fuzzy technique was used in different tasks of DR diabetic
classification such as the preprocessing stage as filtering and histogram equalization and
was used as well in the detection of 4 retinal structures. An accuracy of 0.93, specificity of 1
retinopathy
and sensitivity of 0.8679 were achieved using k-NN [19]. Gaussian mixture was used for stage
region segmentation; AlexNet was used for features extraction, linear discriminant analysis
and principal component analysis (PCA) for features selection and finally SVM for
classification of DR. The best achieved accuracy was 97.93% with sensitivity of 1 and
specificity of 0.93 [20].
Based on deep learning, PCA was used to reduce the dimensionality, followed by grey wolf
optimization to select the optimal parameters and finally deep neural network was trained on
Debrecen dataset from UCI machine learning repository to classify the extracted features into
“affected with DR” or not. The achieved accuracy was 97.3% with sensitivity of 91% and
specificity of 97% [21]. CNN was trained on the Kaggle fundus images dataset to classify DR
and achieved an accuracy of 75%, sensitivity of 30% and specificity of 95% [22]. TL based on
pre-trained models was used; GoogLeNet and AlexNet were applied on Kaggle and Messidor-
1 datasets. The achieved accuracies were 74.5%, 68.8% and 57.2% for 2-ary, 3-ary and 4-ary
classification models, respectively [23]. GoogLeNet Inception v3 classifier was applied on
Kaggle dataset. The achieved accuracies were 61.3%, 60.3% and 37.7% for 2-class, 3-class
and 5-class, respectively [24]. Synergic deep learning model was applied on Messidor dataset
to detect DR and classify its severity. It achieved an accuracy of 99.28, sensitivity of 98 and
Specificity of 99 [25]. VGG-16 model was applied on 35,126 images from Kaggle dataset. The
achieved 5-class classification accuracy was 74%, the sensitivity was 80%, the specificity
was 65% and the AUC was 0.80 [26]. DenseNet and vgg-16 were utilized to classify the fundus
images into the 5-stages of DR using 3662 images from Kaggle dataset. The achieved
accuracies were 0.9611 and 0.7326 for DenseNet and vgg-16 respectively [27]. vgg-16 was also
used 3662 images from Kaggle dataset to classify the severity level of DR with accuracy of
84.31%, F1 score of 84 and an AUC of 97 [28]. AlexNet, VGG-16 and SqueezeNet were applied
on 1200 images of MESSIDOR dataset to classify the severity level of DR. The achieved
accuracies were 93.46%, 91.82% and 94.49% respectively; specificity of 94.53, 88.54 and
94.54, respectively; and sensitivity of 92.38, 93.47 and 94.47 [29]. Inception V3, vgg-16 and
ResNet50 were applied on 35,126 images from Kaggle dataset to classify DR into 5 severity
stages; vgg-16 achieved the highest accuracy of 78% [30]. The preprint of this article is
available on [31].

3. The proposed method

In this section, the used data and the proposed model are described. First, the used dataset for
developing the proposed model is presented. Then, the full process, which contains “Pre-
processing the data” and “Developing Transfer Learning-based CNN Model” phases, is
explained. In “Pre-processing the data” phase, the data is prepared for developing CNN model
based on TL approach in the second phase.

3.1 The used dataset

In this research, the proposed model was conducted using the data obtained from the publicly
available benchmark dataset which is the Kaggle dataset [32]. The dataset contains colored
highly diverse levels of illumination in fundus images. A set of 35,126 retinal images from the
Kaggle dataset was used to develop the model.
Kaggle dataset images are in PNG format and they are re-sized to 224 3 224 pixels. Each
image is labeled as left or right eye. Each image is categorized according to the level of DR
ACI severity into one of 5-class labels (0–4) to represent (normal, mild, moderate, severe,
proliferate_DR) stages. Figure 1 shows different samples from Kaggle dataset representing
different stages, where Figure 1(a) is a normal sample and (b)-(e) samples represent different
stages of severity.

3.2 Pre-processing the data

To develop the proposed CNN model based on TL approach, pre-processing steps were
applied on the retinal fundus images to prepare the images for the learning phase. The pre-
processing steps can be summarized as follow:
(1) The retinal fundus image region was cropped automatically from each image to
remove the background and unwanted region. Figure 2(a) shows a sample of an
original image from the Kaggle dataset, while Figure 2(b) shows the same image after
removing unwanted region.
(2) One of the most important challenges in the development of a deep learning model is
the unbalanced and limited data size. In this research, the used data does not suffer

Figure 1.
Samples from Kaggle
dataset representing
different stages of DR
severity (a) No_DR (b) Mild (c) Moderate (d) Severe (e) Proliferate_DR
52_left 231_left 13038_left 35285_left 24853_right

(a) Original image (b) After cropping

Figure 2.
Pre-processing steps
for one image from the
proliferate_DR images Rotate 90 Rotate 180 Rotate 270 Flipped
of the Kaggle dataset
(c) Rotation of a cropped image by different orientations
 from data limitation especially that the adopted approach for learning is TL which Classifying
relatively overcomes the data limitation problem. However, as it is clear from Table 1 diabetic
that there is a balancing problem in the used data where the representation of the
classes is unbalanced. The images in class 3 and 4 do not have enough representation
retinopathy
as the other classes which are an obstacle in the way of detection of the cases stage
belonging to these classes. Therefore, augmentation was applied to the poorly
represented classes which are 3 and 4 to solve the data balancing problem. Thus, each
training image belonging to these classes was rotated by three angles of 908, 1808 and
2708 and then flipped to enlarge the representation of these classes in the dataset.
Column 4 in Table 1 shows the number of images in different classes after
augmentation. Figure 2(c) shows the augmentation by different orientations of the
sample in Figure 2(b) which belongs to proliferate_DR (class 4) in the Kaggle dataset.
(3) All images were re-sized to the same size to satisfy the CNN requirement of equally
sized images that are provided as input to CNN model.

3.3 Developing transfer learning-based CNN model

TL is to utilize a pre-trained model to train another model. The pre-trained models such as
VGG, ResNet and Inception are trained on ImageNet which is a large dataset. The developers
of these models provided their models publicly to enable more research on the use of these
representations in computer vision. Where these pre-trained models contain many millions of
parameters in their architectures, training them from scratch requires very long
computational time and huge number of input images. So, TL is the best solution to many
problems where it can exploit pre-trained models to solve other problems such as the one
presented in this research. The used TL architecture is shown in Figure 3. As shown in the
figure, the pre-trained CNN model was trained using ImageNet which is a large public dataset
that contains 1,000,000 images to be classified into 1,000 classes. The retinal fundus dataset
was utilized to train the pre-trained network, after applying pre-processing on it.
The top 2 layers of the pre-trained model, which are employed to classify 1000 classes,
were removed and replaced by an output layer with SoftMax activation function as a
classifier with 5-nodes to supply 5 output classes, which represent the stages of DR. The 5
nodes can be changed to (2–4) nodes according to the different combinations of severity
groupings to specify the required output as will be shown in “Experimental Results” section.
The residual components of CNN were handled as features extractor for the new dataset,
while the pre-trained model weights were kept unchanged. The new network was re-trained
with retinal fundus images dataset with learning rate of 0.001 and Adam optimizer, while the
number of epochs was (10–20) epochs.
In this research, TL-based model was developed to classify the retinal fundus images
dataset into the different stages of DR severity levels. The three most common pre-trained
models which are VGG, ResNet and Inception were used to classify the Kaggle dataset into its
five severity levels. Where VGG achieved the best result in this task, it was used as the

No. of classes DR classification No. of images No. of images after augmentation

0 No_DR 25,810 25,810

1 Mild 2,443 2,443
2 Moderate 5,292 5,292 Table 1.
3 Severe 873 4,365 The distribution of the
4 proliferate_DR 708 3,540 different classes in
Total 35,126 41,450 Kaggle database
ACI

…
.

output

Large public dataset

Transferred learning weights

Image
preprocessing
Figure 3.
Transfer learning
architecture output
Small dataset

adopted model in this research and so it was further investigated by performing several
experiments where they classify the dataset into different combinations of classes.
VGG-16 is composed of 16 depth layers. The input to VGG-16 is a (224 3 224) size image.
The network contains a set of convolutional filters with (3 3 3) size. A stride of 1 pixel is used
for all convolution filters, the padding is 1 pixel for (3 3 3) convolutional filters. The
rectification (ReLU) activation function is used for all hidden layers. Five of convolutional
layers are followed by (2 3 2) max-pooling layers with a stride of 2. Finally, 2 fully connected
(FC) layers with 4096 channels each are applied, followed by the output of 1000 channels (one
for each class) with soft-max activation function.

4. Experimental results
This section demonstrates the analysis and the experimental results of the proposed model.
To validate the efficiency of the proposed model and to compare the results with others,
benchmark dataset was used for implementation. Keras Python deep learning library on top
of TensorFlow framework was used for implementing the model based on VGG with 16
layers (VGG-16) on a machine with an Intel® Core™ i7 CPU@ 3.6 GHz with 32 GB RAM and a
Titan X Pascal Graphics Processing Unit (GPU). Extensive experiments were conducted to
get the best setting that achieves the best results.
The dataset was randomly split into training and test sets, where the training dataset
represents 70% of the whole data and the remaining 30% was used to test the model. The
classification model was implemented according to the proposed architecture previously
described using the training dataset and tested using test data. As mentioned before, the
proposed model was applied using the three most common pre-trained models which are
ResNet, Inception and VGG to classify the retinal fundus images of the Kaggle dataset into
the five severity levels. The achieved accuracies were 66.24%, 63.41% and 73.7% for
ResNet50, Inception and VGG-16, respectively. Table 2 shows the achieved accuracies of the
used pre-trained models and the input shape required for each model. Since VGG-16 achieved
the best result, it was used as the adopted model and hence used for more experiments where
it classifies the dataset into different combinations of classes, as will be shown below.
 First, to test the capability of the proposed model to detect abnormality in general, Classifying
experiment #1 was conducted. It is a binary classification task, where it classifies the cases diabetic
into normal and abnormal that includes the other 4-classes which are {mild, moderate, severe,
proliferate_DR}. So, these 4-classes were merged into 1-class which is abnormal class. The
retinopathy
achieved accuracy of this experiment was 75.5% in detecting abnormality. stage
As mentioned before, each image in the Kaggle dataset is categorized into one of the
5-classes (0–4) according to the level of severity to represent (normal, mild, moderate,
severe, proliferate_DR) stages. To test the capability of the model to classify the cases into
the different 5 severity levels, experiment #2 was conducted. The achieved accuracy
was 73.7%.
According to the consulted ophthalmologists, in Kaggle database the mild cases did not
form an obvious class as some of its cases could be classified as normal while others were
more likely to belong to moderate. So, it was suspected that the model might not be able to
distinguish them from normal and moderate classes. Likewise, the severe and proliferative
were not easily distinguishable. Therefore, in experiment #3, “normal” and “mild” cases; and
“severe” and “proliferative” cases were merged. And, in experiment #4, “mild” and
“moderate” cases; and “severe” and “proliferative” cases were merged. The achieved
accuracies were 80.5% and 76.4%, respectively, which proves that the differentiating traits
for the mild class are not evident and the classification of classes of the dataset is not accurate.
The increment in the accuracy in experiment #3 compared to experiment #4, clarifies that the
mild class is closer to normal class, which may be translated that the number of cases in
the mild class that inclines to the normal class are more than the ones that inclines to the
moderate class.
In another approach, there was the intention to determine the severity level among the
abnormal cases only, neglecting the normal cases. In experiment #5, the model classified the 4
abnormal classes. The achieved accuracy was 63.5%. The reduction in the accuracy
compared to experiment #2 is due to the absence of the “normal" class which is proved to be
clearly distinct. Due to the mentioned classes convergence, merging between classes was
applied excluding the “normal” cases again. So, in experiment #6 mild was merged with
moderate, while severe was merged with proliferate_DR. The achieved accuracy improved
to 85.78%.
By consulting ophthalmologists, we found that the 4 stages of abnormality can be mainly
categorized into proliferative diabetic retinopathy (PDR) and non-proliferative diabetic
retinopathy (NPDR) according to severity level. Therefore experiment#7 was conducted by
classifying cases into proliferate_DR and Non-Proliferative {mild, moderate, severe}. The
achieved accuracy was 86.5%. Table 3 shows the results of different experiments of the
model built using TL based on VGG-16. The used metrics for evaluation are as follow:
TP
Recallð%Þ ¼ (1)
TP þ FN
Tp
Precision ð%Þ ¼ (2)
TP þ FP

Model Input shape Accuracy% Table 2.

The accuracies of
ResNet50 224 3 224 66.24 different models in the
Inception (GoogLeNet) 299 3 299 63.41 classification of Kaggle
VGG-16 224 3 224 73.7 dataset
ACI TP þ TN
Accuracy ð%Þ ¼ (3)
TP þ FP þ TN þ FN
2 TP
F1 ¼ (4)
2TP þ FP þ FN
where TP is true-positive value, FP is false-positive value, TN is true negative value and FN is
false-negative value.

5. Discussion
Detecting DR and the classification of its severity stages are one of the biggest challenges for
ophthalmologists. The contribution of this work is to develop a model that helps in detecting
DR and classifying its different stages. Since the available number of cases in different DR
datasets are relatively limited, so, TL is the suitable approach for the proposed work to
employ pre-trained models to build the model that can classify the DR cases using the
available data.
To evaluate the proposed work, it was compared with previous works that used TL
applied on the same dataset, which is Kaggle dataset, for a fair comparison as illustrated in
Table 4. Chowdhury et al. [24] used GoogLeNet to classify DR into 2, 3 and 5 classes and the
achieved accuracies are 61.3, 60.3 and 37.7 respectively. Lam et al. [23] applied AlexNet and
GoogLeNet TL approach, but they stated that GoogLeNet achieved better accuracies than
AlexNet, which were 74.5, 68.8 and 57.2 for 2, 3 and 4 classes respectively. Although the two
researches [23, 24] used the same model which is GoogLeNet and the same dataset, the results
of the two researches are different. That may be resulted from different preprocessing steps
and changes in the setting of TL-network. Pratt et al. [22] built CNN using Kaggle dataset to

No of F1
Exp Categorization classes Accuracy Recall Precision score

1 (Normal; 2 75.5 71.7 72.97 70.48

Mild þ Moderate þ Severe þ Proliferation)
2 (Normal; mild; moderate; severe; proliferation) 5 73.7 67.82 66.85 64.28
3 (Normal þ Mild; moderate; 3 80.5 76.14 74.5 73.86
Severe þ Proliferation)
4 (Normal; Mild þ Moderate; 3 76.4 69.6 70.23 67.94
Table 3. Severe þ Proliferation)
The results of different 5 (Mild; moderate; severe; proliferation) 4 63.5 63.5 64.3 62.5
experiments built 6 (Mild þ Moderate; Severe þ Proliferation) 2 85.78 84.9 87.14 85.8
using VGG-16 7 (Mild þ Moderate þ Severe; proliferation) 2 86.5 88.05 92.18 90.067

Accuracy
Reviewed studies Used technique 2-Class 3-Class 4-Class 5-Class

Chowdhury et al. [24] TL Google’s Inception v3 61.3% 60.3% 37.7%

Lam et al. [23] TL Google’s Inception 74.5% 68.8% 57.2%
Table 4. Pratt et al. [22] CNN 75%
Comparison between Thota and Reddy [26] VGG-16 75%
proposed work and Pradhan et al. [30] VGG-16 78%
related works Proposed model TL VGG-16 75.5% 80.5% 63.5% 73.7%
classify the cases into the 5 classes and the achieved accuracy was 75%. Thota and Reddy Classifying
[26] used VGG-16 to classify Kaggle dataset into the 5 classes and the achieved accuracy was diabetic
75%. Pradhan et al. [30] also used the VGG-16 to classify Kaggle dataset into 5 severity stages
with an accuracy of 78%. As it is shown, the proposed model results outperform the two
retinopathy
works that used the same dataset and TL approach but with GoogLeNet. The third, fourth stage
and fifth works are better than the proposed model in classifying the cases into 5 classes
which is the only applied classification in these researches. The third and fourth achieved an
accuracy of 75%, although they used different models which are CNN and TL using VGG-16,
respectively, but the proposed model achieved an accuracy of 73.7%.
It is worth noting that, by applying the proposed model without augmentation the results
of different experiments were better, but it was suffering from overfitting. That was clear
from that the results of different experiments that remained with the same accuracy through
all epochs, even by using different models which are VGG-16, ResNet50 and Inception. As an
example, they all achieved 75% to classify DR into 5 severity stages (experiment # 2) and
91.93% for PDR and NPDR (experiment # 7).

6. Conclusion and future work

Recently, the number of diabetes patients has increased dramatically and consequently the
number of DR patients has increased. To help in the detection of DR and classification of its
grade stages, deep learning was used, in this research. The TL approach, which utilized the
VGG-16 pre-trained CNN model, was applied on Kaggle retinal fundus images dataset. The
pre-trained VGG-16 model was used for feature extraction, then the top 2-layers were
replaced by SoftMax activation function with the new output layer which changed to 2–5
classes according to the experiment.
According to the results of different experiments, it was concluded that the borderline
between different classes is not sharp specially between mild and normal, and also between
severe and proliferative. And even the ophthalmologists suffer from the difficult
distinguishing between these classes. So, more work in the future is needed to find more
accurate techniques or models to extract the subtle features that can distinguish between
different classes. The proposed architecture can also be applied on other datasets to
investigate the behavior of the model with the similar severity groupings. This is a possible
topic for future work. Application of the model in real life can be beneficial in diagnosis and
prevention of complications of DR.

References
1. [Link]
2. Yau J.W., et al. Global prevalence and major risk factors of diabetic retinopathy. Diabetes Care.
2012; 35(3): 556-64.
3. Flaxman S.R., et al. Global causes of blindness and distance vision impairment 1990–2020: a
systematic review and meta-analysis. The Lancet Glob Health. 2017; 5(12): e1221-34.
4. Bourne R.R., et al. Causes of vision loss worldwide, 1990–2010: a systematic analysis. The Lancet
Glob Health. 2013; 1(6): e339-49.
5. Philip S., et al. The efficacy of automated “disease/no disease” grading for diabetic retinopathy in
a systematic screening programme. Br J Ophthalmol. 2007; 91(11): 1512-7.
6. Mookiah M.R.K., et al. Computer-aided diagnosis of diabetic retinopathy: a review. Comput Biol
Med. 2013; 43(12): 2136-55.
7. Litjens G., et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;
42: 60-88.
ACI 8. Kharazmi P., et al. A computer-aided decision support system for detection and localization of
cutaneous vasculature in dermoscopy images via deep feature learning. J Med Syst. 2018;
42(2): 33.
9. Oquab M., et al. Learning and transferring mid-level image representations using convolutional
neural networks. Proceedings of the IEEE conference on computer vision and pattern
recognition; 2014.
10. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition.
University of Oxford and Google DeepMind. arXiv preprint arXiv:1409.1556; 2014.
11. Szegedy C, et al. Rethinking the inception architecture for computer vision. Proceedings of the
IEEE conference on computer vision and pattern recognition; 2016.
12. Szegedy C, et al. Going deeper with convolutions. Proceedings of the IEEE conference on
computer vision and pattern recognition; 2015.
13. He K, et al. Deep residual learning for image recognition. Proceedings of the IEEE conference on
computer vision and pattern recognition; 2016.
14. Zoph B, et al. Learning transferable architectures for scalable image recognition. Proceedings of
the IEEE conference on computer vision and pattern recognition; 2018.
15. Russakovsky O., et al. Imagenet large scale visual recognition challenge. Int J Comput Vis. 2015;
115(3): 211-52.
16. Krizhevsky A., Sutskever I., Hinton G.E. Imagenet classification with deep convolutional neural
networks. Adv Neural Inf Process Syst. 2012; 25: 1097-105.
17. Seoud L, C. J., Cheriet F. Automatic grading of diabetic retinopathy on a public database.
Proceedings of the ophthalmic medical image analysis second international workshop. Munich; 9
October 2015.
18. Cao W, Shan J., Czarnek N., Li L. Microaneurysm detection in fundus images using small image
patches and machine learning methods. Proceedings of the IEEE International Conference on
Bioinformatics and Biomedicine (BIBM), 13–16 November 2017, Kansas City, MO, USA.
p. 325-31.
19. Rahim S.S., et al. Automatic screening and classification of diabetic retinopathy and maculopathy
using fuzzy image processing. Brain Inform. 2016; 3(4): 249-267.
20. Mansour R.F. Deep-learning-based automatic computer-aided diagnosis system for diabetic
retinopathy. Bio Eng Lett. 2018; 8(1): 41-57.
21. Gadekallu T.R., et al. Deep neural networks to predict diabetic retinopathy. J. Ambient Intell.
Humaniz. Comput. 2020.
22. Pratt H., et al. Convolutional neural networks for diabetic retinopathy. Procedia Comp Sci. 2016;
90: 200-5.
23. Lam C., et al. Automated detection of diabetic retinopathy using deep learning. AMIA summits on
translational science proceedings. 2018; 2018: 147.
24. Chowdhury M.M.H., Meem N.T.A. A machine learning approach to detect diabetic retinopathy
using convolutional neural network. Proceedings of International Joint Conference on
Computational Intelligence. Springer; 2020.
25. Kathiresan S., et al. Automated detection and classification of fundus diabetic retinopathy images
using synergic deep learning model. Pattern Recogn. Lett. May 2020; 133: 210-216.
26. Thota N.B., Reddy D.U. Improving the accuracy of diabetic retinopathy severity classification
with transfer learning. 2020 IEEE 63rd international midwest symposium on circuits and systems
(MWSCAS). IEEE; 2020.
27. Mishra S., Hanchate S., Saquib Z. Diabetic retinopathy detection using deep learning. 2020
International Conference on Smart Technologies in Computing, Electrical and Electronics
(ICSTCEE). IEEE; 2020.
28. Bodapati J.D., Shaik N.S., Naralasetti V. Deep convolution feature aggregation: an application to Classifying
diabetic retinopathy severity level prediction. Signal, Image and Video Proc. 2021: 1-8.
diabetic
29. Rehman M.U., et al. Classification of diabetic retinopathy images based on customised CNN
architecture. 2019 Amity International Conference on Artificial Intelligence (AICAI). IEEE; 2019.
retinopathy
30. Pradhan A., et al. Transfer learning based classification of diabetic retinopathy stages. 2020
stage
International Conference on Computational Performance Evaluation (ComPE). IEEE; 2020.
31. El Houby M.F. Using transfer learning for diabetic retinopathy stages classification. PREPRINT
(Version 1) available at Research Square; 30 Apr, 2021.
32. [Link]

About the author

Enas M.F. El Houby has received Electrical Communication Engineering [Link]. degree
from Mansura University; [Link]. in Computer science from Cairo University where the
thesis was an output of a collaboration project with Michigan state University in USA,
and Ph.D. degrees in Computer science from Cairo University. She is currently an
Associate Professor in the Department of Systems and Information, Engineering
Research Division, National Research Centre. Her research interests are focused on
Artificial intelligence, knowledge discovery and data mining, machine learning
techniques, bioinformatics, semantics and information retrieval. Also, she is interested
in computer-aided diagnosis (CAD) systems. Enas M.F. El Houby can be contacted at: enas_mfahmy@
[Link]; [Link]@[Link]

For instructions on how to order reprints of this article, please visit our website:
[Link]/licensing/[Link]
Or contact us for further details: permissions@[Link]