SlideShare a Scribd company logo
|| JAI SRI GURUDEV ||
SRI ADICHUNCHANAGIRI SHIKSHANA TRUST ®
SJB INSTITUTE OF TECHNOLOGY
BGS HEALTH & EDUCATION CITY, KENGERI, BENGALURU-560060
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
Under the Guidance of
Mrs Rajatha
Associate Professor
Dept. of CSE
Presented By:
Manasa M [1JB21CS414]
Punith HN [1JB21CS419]
Rahul V Sanka [1JB21CS420]
Sarath Kumar V [1JB21CS422]
Project Work Phase – I
Presentation On
“Severity detection of Diabetic retinopathy Using
Deep Learning Algorithms”
Severity detection of Diabetic retinopathy using ML 1
AGENDA CONTENTS
1. Abstract
2. Introduction
3. Literature Survey
4. Problem Statement
5. Challenges
6. Motivation
7. Objectives
8. Design and Architecture
9. Methodology
10.Implementation
11.Conclusion
12.References
Severity detection of Diabetic retinopathy using ML
1
ABSTRACT
There are several deep learning techniques that are used to perform the predictive analytics over big
data in various medical tasks. Predictive analytics in medical healthcare is a challenging task yet
ultimately helping the practitioners handle big data-informed timely decisions about patient’s
medical health and treatment. This project discusses the predictive analytics in healthcare. Patient’s
medical record is obtained for experimental research. The two architectures of deep learning are
implemented. Performance and accuracy of these applied algorithms are implemented and
compared. Different deep learning techniques used in this research that reveals which algorithm is
best suited for the prediction of diabetes over the patient. This project aims to help doctors and
practitioners in early stage to predict diabetic retinopathy using deep learning techniques.
Severity detection of Diabetic retinopathy using ML
2
 Healthcare industry is a very large and sensitive meta data and must be carefully
handled. One of the growing extremely fatal diseases all over the world is
Diabetes Mellitus.
 Some of the useful deep learning techniques for examining the data from diverse
perspectives and synopsizing it into valuable information. The accessibility and
availability of huge amounts of data are able to provide us useful knowledge
unless certain data mining techniques are applied to it.
 The Deep Learning consists of an algorithm called Convolutional Neural
Network(ConvNet/CNN) which gets the input image, assign importance to
various aspects/objects in that image and be able to distinguish one from the other.
INTRODUCTION
Severity detection of Diabetic retinopathy using ML
3
Severity detection of Diabetic retinopathy using ML
 Mild nonproliferative diabetic retinopathy: This is the earliest stage of diabetic retinopathy,
characterized by tiny areas of swelling in the blood vessels of the retina. These areas of swelling
are known as micro aneurysms. Small amounts of fluid can leak into the retina at this stage,
triggering swelling of the macula. This is an area near the center of the retina.
 Moderate nonproliferative diabetic retinopathy: Increased swelling of tiny blood vessels starts
Severity detection of Diabetic retinopathy using ML 5
Severity detection of Diabetic retinopathy using ML 7
Severity detection of Diabetic retinopathy using ML
6
Authors Year of
publication
Title of the paper Methodology Limitations
Balla Goutam
Mohammad
Farukh Hashmi
(Senior
Member,Ieee),
Zong
WooGeem ,
(Senior
Member, Ieee),
and Neeraj
DhanrajBokde
2022 A Comprehensive
Review of Deep
Learning
Strategies in Retinal
Disease Diagnosis
Using Fundus Images
The proposed review focuses mainly
on providing in depth review of
various DL strategies recently
implemented
for retinal disease diagnosis using
fundus images. This study
also intends to outline possible
future directions for new
researchers interested in AI-based
retinal disease diagnosis.
The models trained on IDRID ,
Messidor, DRIVE datasets may
not perform well on other
datasets. These may not be
suitable for efficient model
training,
JingWang, Liu
Yang, Zhanqian
Huo, Weifeng
He, and Junwei
Luo
2020 Multi-Label
Classification of Fundus
Images With
EfficientNet.
The purpose of this study is to
establish a framework for automatic
identification of multilabel fundus
diseases, and to achieve it by
designing a corresponding ensemble
model.
The amount of data for some
diseases is very limited, which
makes it very difficult to
improve the performance of a
network. Another basic
limitation comes from the black
box of the nature of deep
networks. The network
automatically learns features
from images, but the specific
features learned are unknown.
LITERATURE SURVEY
Severity detection of Diabetic retinopathy using ML 9
Ayesha Kazi, Prerna
Sukhija, Miloy Ajmera,
Kailas Devadkar
2021 Processing Retinal
Images to Discover
Diseases
This paper aims to not only
accurately classify the disease
into one of the three possible
abnormalities or assert that
it is a healthy retina. The image may
fall into more than
one category. For example, a retina
which shows any
presence of Diabetic Retinopathy
could also show hints of Glaucoma
It cannot determine the
presence of a variation in
the image
(like highlighting,
tessellation etc) preceding
the
classification step, for
training the neural network,
and to
use unique combinations
for different cases.
Juan Carrillo
, Lola Bautista, Jorge
Villamizar, Juan Rueda,
Mary Sanchez and
Daniela Rueda
2021 Glaucoma Detection
Using Fundus Images
of The Eye
This work presents a computational
tool for automatic glaucoma
detection from fundus images of the
eye. This work propose a
novel method for cup segmentation,
which shows an improvement
in the accuracy compared to other
methods
The vessels segmentation
requires an
improvement due to some
fails in different images and
residual
noise after the
segmentation.
Severity detection of Diabetic retinopathy using ML 10
PROBLEM STATEMENT
The problem addressed in this study is the need for a cost-effective and scalable solution for the
detection of diabetic retinopathy (DR), a leading cause of blindness in adults with diabetes.
Current methods for DR detection are time-consuming, expensive, and require specialized
equipment and trained personnel, making them inaccessible in many regions. The objective of this
study is to develop and evaluate a deep learning model for automated DR detection from retinal
images, which can improve the accessibility and affordability of DR screening and diagnosis
Severity detection of Diabetic retinopathy using ML 8
CHALLENGES
Severity detection of Diabetic retinopathy using ML 12
Designing a severity detection system for diabetic retinopathy using AI and machine learning involves
several challenges. Here are some of the common challenges faced in this domain:
1. Limited and Imbalanced Data:
- Insufficient and imbalanced datasets can hinder the training of effective models. Diabetic retinopathy
severity levels may not be evenly distributed, leading to biases in the model.
2. Annotation Variability:
- Annotating the severity levels of diabetic retinopathy can be subjective, and different experts may
provide varying annotations. Achieving a consensus among annotators and ensuring a standardized dataset
is challenging.
3. Interpretability and Explain ability:
- AI models, particularly deep learning models, are often considered black boxes. It's crucial to interpret
and explain the decisions made by the model, especially in medical applications where transparency is
essential for gaining trust from healthcare professionals.
4. Generalization Across Diverse Populations:
- Models trained on data from a specific population may not generalize well to other populations with
different demographics, ethnicities, or healthcare practices. Robustness and generalizability across diverse
patient groups are critical considerations.
Severity detection of Diabetic retinopathy using ML 13
5. Integration with Clinical Workflow
- Integrating AI systems into the existing clinical workflow can be challenging. Ensuring that the
severity detection system seamlessly fits into the diagnostic process and complements the workflow of
healthcare professionals is crucial for successful implementation.
6. Ethical and Legal Considerations
- Handling patient data raises ethical concerns, and there are legal and privacy considerations when
working with medical information. Compliance with data protection regulations and the establishment of
secure systems are essential.
7. Real-time Processing
- In clinical settings, real-time processing is often required. Designing models that can provide timely
and accurate predictions is challenging, especially when dealing with high-resolution medical images.
8. Robustness to Image Quality
- Medical images can vary in quality due to factors such as equipment differences, variations in lighting
conditions, and patient characteristics. Ensuring that the model is robust to variations in image quality is
essential for reliable predictions.
9. Continuous Learning and Adaptability
- Healthcare data is dynamic, and patterns may change over time. Designing models that can adapt to
new data and continuously learn from evolving patterns in diabetic retinopathy is a significant challenge.
Severity detection of Diabetic retinopathy using ML 14
MOTIVATION
The motivation behind developing a deep learning model for diabetic retinopathy detection is the
significant burden of this disease on patients, healthcare systems, and society. Early detection and
treatment of DR are critical to preventing blindness and improving patient outcomes. However,
current methods for DR detection are expensive and inaccessible in many regions, leading to
delays in diagnosis and treatment. By developing a cost-effective and scalable solution for DR
detection using deep learning, this study aims to improve the accessibility and affordability of DR
screening and diagnosis, ultimately improving patient outcomes and reducing the burden on
healthcare systems.
OBJECTIVES
1.To develop a deep learning model for automated diabetic retinopathy (DR) detection from
retinal images.
2. To compare the performance of the deep learning model with other state-of-the-art DR
detection methods to assess its superiority and effectiveness.
3. To assess the clinical implications of the developed deep learning model, including early
detection and treatment of DR, reducing the workload of ophthalmologists, and improving
patient outcomes.
4. To identify any limitations or challenges faced in the development and evaluation of the deep
learning model, such as limited sample size or biased data, that may affect the generalizability
of the model.
5. To provide recommendations for future research in the field of DR detection using deep
learning, such as the implementation and validation of the model in real-world clinical settings.
Severity detection of Diabetic retinopathy using ML 7
DESIGN AND ARCHITECTURE
A system architecture for diabetic retinopathy detection using deep
learning may involve several components, including:
 1. Image acquisition: A retinal camera or imaging device is used to
acquire high-quality retinal images of patients.
 2. Preprocessing: Image preprocessing techniques such as noise
reduction, contrast adjustment, and image enhancement are applied to
the retinal images to improve image quality.
 3. Feature extraction: Deep learning algorithms are used to extract
relevant features from the preprocessed images.
Severity detection of Diabetic retinopathy using ML 16
 4. Training and validation: A deep learning model is trained on a large
dataset of retinal images with known diabetic retinopathy labels. The
model is validated on a separate dataset to assess its performance.
 5. Testing and evaluation: The trained model is tested on new retinal
images to assess its diagnostic accuracy and performance.
 6. User interface: A user-friendly interface is developed to enable
healthcare professionals to interact with the system and input patient
information.
 7. Patient database: A patient database is maintained to store patient
information and retinal images for future reference.
Severity detection of Diabetic retinopathy using ML 17
 8. Reporting: A reporting module is developed to generate reports
summarizing the results of diabetic retinopathy detection and
classification for each patient.
 9. Integration with EHRs: The system is integrated with electronic
health records (EHRs) to facilitate patient care and management.
 10. System maintenance and updates: The system is designed for easy
maintenance and updates to ensure optimal performance and accuracy
over time.
Severity detection of Diabetic retinopathy using ML 18
Convolutional Neural Networks
 A CNN is type of a DNN consists of multiple hidden layers such as
convolutional layer, RELU layer, Pooling layer and fully connected a
normalized layer.
 CNN shares weights in the convolutional layer reducing the memory
footprint and increases the performance of the network.
 The important features of CNN lie with the 3D volumes of neurons,
local connectivity and shared weights.
 A feature map is produced by convolution layer through convolution of
different sub regions of the input image with a learned kernel. Then,
anon- linear activation function is applied through ReLu layer to
improve the convergence properties when the error is low.
Severity detection of Diabetic retinopathy using ML 19
 In pooling layer, a region of the image/feature map is chosen and the
pixel with maximum value among them or average values is chosen as
the representative pixel so that a 2x2 or 3x3 grid will be reduced to a
single scalar value. This results a large reduction in the sample size.
Sometimes, the traditional Fully-Connected (FC) layer will be used in
conjunction with the convolutional layers toward the output stage
Severity detection of Diabetic retinopathy using ML 20
 A CNN is composed of several kinds of layers:
 Convolutional layer:
Creates a feature map to predict the class probabilities for each feature by
applying a filter that scans the whole image, few pixels at a time.
 Pooling layer (down-sampling):
scales down the amount of information the convolutional layer generated for
each feature and maintains the most essential information.
 Fully connected input layer:
flattens the outputs generated by previous layers to turn them into a single
vector that can be used as an input for the next layer.
 Fully connected layer:
Applies weights over the input generated by the feature analysis to predict an
accurate label.
Severity detection of Diabetic retinopathy using ML 21
Severity detection of Diabetic retinopathy using ML 22
Convolutional Neural Network General Architecture
DATA FLOW DIAGRAM
Severity detection of Diabetic retinopathy using ML 23
METHODOLOGY
Severity detection of Diabetic retinopathy using ML 14
Detecting Diabetic Retinopathy:
 Diabetic retinopathy can be detected by using the Retina of the eyes. The eyes having
the retina, inside the retina lots of blood vessels are present.
 The retina of diabetic patients is different from the normal patient. The blood vessels
are chocked inside the retina that indicate the patient has a diabetic.
 By using cnn we have detected the leaking blood vessels.
 By using pixels images are classified into the part of color sheds. If the blood vessels
anywhere choked or leaked then that classified image easily detected the changes into
the image.
 Then the algorithm detects if the patient has Diabetic Retinopathy or not.
Severity detection of Diabetic retinopathy using ML 15
IMPLEMENTATION
Steps for Implementation
 Front-End Development Using Python Flask:
Modern computer applications are user-friendly. User interaction is
not restricted to console- based I/O. They have a more ergonomic
graphical user interface (GUI) thanks to high-speed processors and
powerful graphics hardware.
These applications can receive inputs through mouse clicks and can
enable the user to choose from alternatives with the help of radio
buttons, dropdown lists, and other GUI elements.
Severity detection of Diabetic retinopathy using ML 26
 Flask Programming:
 Flask is the standard GUI library for Python. Python when
combined with Flask provides a fast and easy way to create GUI
applications. Flask provides a powerful object- oriented interface
to the Tk GUI toolkit. Flask has several strengths.
 It’s cross- platform, so the same code works on Windows,
macOS, and Linux. Visual elements are rendered using native
operating system elements, so applications built with Flask look
like they belong on the platform where they’re run.
Severity detection of Diabetic retinopathy using ML 27
 The goals of implementation are as follows.
Minimize the memory required.
Maximize output readability.
Maximize source text readability.
Minimize the number of source statements.
Minimize development time
Severity detection of Diabetic retinopathy using ML 28
Conversion from RGB to grayscale
 Advantages of converting RGB color space to gray
 To store a single-color pixel of an RGB color image we will need
8*3 = 24 bits (8 bit for each color component).
 Only 8 bit is required to store a single pixel of the image. So we
will need 33 % less memory to store grayscale image than to store
an RGB image.
 Grayscale images are much easier to work within a variety of task
like In many morphological operation and image segmentation
problem, it is easier to work with single layered image (Grayscale
image) than a three-layered image (RGB color image).
 It is also easier to distinguish features of an image when we deal
with a single layered image
Severity detection of Diabetic retinopathy using ML 29
CONCLUSION
 Diabetic retinopathy is a leading cause of blindness in diabetic patients, and
early detection and treatment are crucial for preventing vision loss. Deep
learning algorithms have shown great potential in detecting and classifying
diabetic retinopathy from retinal images, which can aid in the early diagnosis
and management of the disease. The proposed system for diabetic retinopathy
detection using deep learning has the potential to provide accurate and timely
diagnoses, which can improve patient outcomes and reduce healthcare costs.
While there are still challenges to be addressed, such as the need for large and
diverse datasets and interpretability of deep learning models, the advancements
in this field continue to offer promise for improving diabetic retinopathy
detection and treatment.
Severity detection of Diabetic retinopathy using ML 28
REFERENCE
 1. Abràmoff, M. D., Lou, Y., Erginay, A., Clarida, W., Amelon, R., Folk, J. C., & Niemeijer, M.
(2016). Improved automated detection of diabetic retinopathy on a publicly available dataset
through integration of deep learning. Investigative Ophthalmology & Visual Science, 57(13),
5200-5206.
 2. Bhaskaranand, M., Ramachandra, C., Bhat, S., & Cuadros, J. (2020). Automated diabetic
retinopathy screening and monitoring using deep learning. Journal of Healthcare Engineering,
2020, 1-13.
 3. Burlina, P. M., Joshi, N., Pekala, M., Pacheco, K. D., Freund, D. E., Bressler, N. M., & Wong,
T. Y. (2017). Automated grading of age-related macular degeneration from color fundus images
using deep convolutional neural networks. JAMA ophthalmology, 135(11), 1170-1176.
 4. Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., ... & Webster,
D. R. (2016). Development and validation of a deep learning algorithm for detection of diabetic
retinopathy in retinal fundus photographs. Jama, 316(22), 2402-2410.
 5. Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C., Liang, H., Baxter, S. L., ... &
Keane, P. A. (2018). Identifying medical diagnoses and treatable diseases by image-based deep
learning. Cell, 172(5), 1122-1131.
 6. Li, Z., Keel, S., Liu, C., He, Y., Meng, W., Scheetz, J., ... & Ting, D. S. (2020). An automated
grading system for detection of vision-threatening referable diabetic retinopathy on the basis of
color fundus photographs. Diabetes care, 43(8), 1748-1755.
Severity detection of Diabetic retinopathy using ML 29
 7. Osareh, A., Shadgar, B., & Markham, R. (2012). A survey of computer-aided
diagnosis of ocular diseases. Computer Methods and Programs in Biomedicine, 108(1),
407-433.
 8. Rajalakshmi, R., Subashini, R., Anjana, R. M., Mohan, V., & Deepa, M. (2018).
Automated diabetic retinopathy detection in smartphone-based fundus photography
using artificial intelligence. Eye, 32(6), 1138-1144.
 9. Ramachandra, C., Bhat, S., & Bhaskaranand, M. (2018). Automated grading of
diabetic retinopathy using deep neural network. Journal of Healthcare Engineering,
2018, 1-14.
 10. Schmidt Erfurth , U., Bogunovic, H., Sadeghipour, A., & Schlegl, T. (2018).
Artificial intelligence in retina. Progress in retinal and eye research, 67, 1-29.
Severity detection of Diabetic retinopathy using ML 30
THANK YOU
Severity detection of Diabetic retinopathy using ML 33

More Related Content

Similar to Diabetic_retinopathy_vascular disease synopsis

Diabetic Retinopathy.pptx
Diabetic Retinopathy.pptxDiabetic Retinopathy.pptx
Diabetic Retinopathy.pptx
NGOKUL3
 
Diabetic Retinopathy.pptx
Diabetic Retinopathy.pptxDiabetic Retinopathy.pptx
Diabetic Retinopathy.pptx
NGOKUL3
 
A Survey on techniques for Diabetic Retinopathy Detection & Classification
A Survey on techniques for Diabetic Retinopathy Detection & ClassificationA Survey on techniques for Diabetic Retinopathy Detection & Classification
A Survey on techniques for Diabetic Retinopathy Detection & Classification
IRJET Journal
 
A Deep Learning Approach for the Detection and Identification of Neovasculari...
A Deep Learning Approach for the Detection and Identification of Neovasculari...A Deep Learning Approach for the Detection and Identification of Neovasculari...
A Deep Learning Approach for the Detection and Identification of Neovasculari...
IRJET Journal
 
EYE DISEASE IDENTIFICATION USING DEEP LEARNING
EYE DISEASE IDENTIFICATION USING DEEP LEARNINGEYE DISEASE IDENTIFICATION USING DEEP LEARNING
EYE DISEASE IDENTIFICATION USING DEEP LEARNING
IRJET Journal
 
IRJET- Approach for Diabetic Retinopathy Analysis using Artificial Neural Net...
IRJET- Approach for Diabetic Retinopathy Analysis using Artificial Neural Net...IRJET- Approach for Diabetic Retinopathy Analysis using Artificial Neural Net...
IRJET- Approach for Diabetic Retinopathy Analysis using Artificial Neural Net...
IRJET Journal
 
A Novel Advanced Approach Using Morphological Image Processing Technique for ...
A Novel Advanced Approach Using Morphological Image Processing Technique for ...A Novel Advanced Approach Using Morphological Image Processing Technique for ...
A Novel Advanced Approach Using Morphological Image Processing Technique for ...
CSCJournals
 
Early Detection of High Blood Pressure and Diabetic Retinopathy on Retinal Fu...
Early Detection of High Blood Pressure and Diabetic Retinopathy on Retinal Fu...Early Detection of High Blood Pressure and Diabetic Retinopathy on Retinal Fu...
Early Detection of High Blood Pressure and Diabetic Retinopathy on Retinal Fu...
IJAAS Team
 
A transfer learning with deep neural network approach for diabetic retinopath...
A transfer learning with deep neural network approach for diabetic retinopath...A transfer learning with deep neural network approach for diabetic retinopath...
A transfer learning with deep neural network approach for diabetic retinopath...
IJECEIAES
 
An automated severity classification model for diabetic retinopathy
An automated severity classification model for diabetic retinopathyAn automated severity classification model for diabetic retinopathy
An automated severity classification model for diabetic retinopathy
IRJET Journal
 
Detection of Diabetic Retinopathy in Retinal Image Early Identification using...
Detection of Diabetic Retinopathy in Retinal Image Early Identification using...Detection of Diabetic Retinopathy in Retinal Image Early Identification using...
Detection of Diabetic Retinopathy in Retinal Image Early Identification using...
ijtsrd
 
Diabetic Retinopathy Detection using Neural Networking
Diabetic Retinopathy Detection using Neural NetworkingDiabetic Retinopathy Detection using Neural Networking
Diabetic Retinopathy Detection using Neural Networking
ijtsrd
 
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
ITIIIndustries
 
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
Carrie Cox
 
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
ijaia
 
Automated Screening of Diabetic Retinopathy Using Image Processing
Automated Screening of Diabetic Retinopathy Using Image ProcessingAutomated Screening of Diabetic Retinopathy Using Image Processing
Automated Screening of Diabetic Retinopathy Using Image Processing
iosrjce
 
IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...
IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...
IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...
IRJET Journal
 
ResNet-n/DR: Automated diagnosis of diabetic retinopathy using a residual neu...
ResNet-n/DR: Automated diagnosis of diabetic retinopathy using a residual neu...ResNet-n/DR: Automated diagnosis of diabetic retinopathy using a residual neu...
ResNet-n/DR: Automated diagnosis of diabetic retinopathy using a residual neu...
TELKOMNIKA JOURNAL
 
IRJET- Detection of Diabetic Retinopathy using Convolutional Neural Network
IRJET- 	  Detection of Diabetic Retinopathy using Convolutional Neural NetworkIRJET- 	  Detection of Diabetic Retinopathy using Convolutional Neural Network
IRJET- Detection of Diabetic Retinopathy using Convolutional Neural Network
IRJET Journal
 
How AI Enhances & Accelerates Diabetic Retinopathy Detection
How AI Enhances & Accelerates Diabetic Retinopathy DetectionHow AI Enhances & Accelerates Diabetic Retinopathy Detection
How AI Enhances & Accelerates Diabetic Retinopathy Detection
Cognizant
 

Similar to Diabetic_retinopathy_vascular disease synopsis (20)

Diabetic Retinopathy.pptx
Diabetic Retinopathy.pptxDiabetic Retinopathy.pptx
Diabetic Retinopathy.pptx
 
Diabetic Retinopathy.pptx
Diabetic Retinopathy.pptxDiabetic Retinopathy.pptx
Diabetic Retinopathy.pptx
 
A Survey on techniques for Diabetic Retinopathy Detection & Classification
A Survey on techniques for Diabetic Retinopathy Detection & ClassificationA Survey on techniques for Diabetic Retinopathy Detection & Classification
A Survey on techniques for Diabetic Retinopathy Detection & Classification
 
A Deep Learning Approach for the Detection and Identification of Neovasculari...
A Deep Learning Approach for the Detection and Identification of Neovasculari...A Deep Learning Approach for the Detection and Identification of Neovasculari...
A Deep Learning Approach for the Detection and Identification of Neovasculari...
 
EYE DISEASE IDENTIFICATION USING DEEP LEARNING
EYE DISEASE IDENTIFICATION USING DEEP LEARNINGEYE DISEASE IDENTIFICATION USING DEEP LEARNING
EYE DISEASE IDENTIFICATION USING DEEP LEARNING
 
IRJET- Approach for Diabetic Retinopathy Analysis using Artificial Neural Net...
IRJET- Approach for Diabetic Retinopathy Analysis using Artificial Neural Net...IRJET- Approach for Diabetic Retinopathy Analysis using Artificial Neural Net...
IRJET- Approach for Diabetic Retinopathy Analysis using Artificial Neural Net...
 
A Novel Advanced Approach Using Morphological Image Processing Technique for ...
A Novel Advanced Approach Using Morphological Image Processing Technique for ...A Novel Advanced Approach Using Morphological Image Processing Technique for ...
A Novel Advanced Approach Using Morphological Image Processing Technique for ...
 
Early Detection of High Blood Pressure and Diabetic Retinopathy on Retinal Fu...
Early Detection of High Blood Pressure and Diabetic Retinopathy on Retinal Fu...Early Detection of High Blood Pressure and Diabetic Retinopathy on Retinal Fu...
Early Detection of High Blood Pressure and Diabetic Retinopathy on Retinal Fu...
 
A transfer learning with deep neural network approach for diabetic retinopath...
A transfer learning with deep neural network approach for diabetic retinopath...A transfer learning with deep neural network approach for diabetic retinopath...
A transfer learning with deep neural network approach for diabetic retinopath...
 
An automated severity classification model for diabetic retinopathy
An automated severity classification model for diabetic retinopathyAn automated severity classification model for diabetic retinopathy
An automated severity classification model for diabetic retinopathy
 
Detection of Diabetic Retinopathy in Retinal Image Early Identification using...
Detection of Diabetic Retinopathy in Retinal Image Early Identification using...Detection of Diabetic Retinopathy in Retinal Image Early Identification using...
Detection of Diabetic Retinopathy in Retinal Image Early Identification using...
 
Diabetic Retinopathy Detection using Neural Networking
Diabetic Retinopathy Detection using Neural NetworkingDiabetic Retinopathy Detection using Neural Networking
Diabetic Retinopathy Detection using Neural Networking
 
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
 
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
Annotating Retina Fundus Images for Teaching and Learning Diabetic Retinopath...
 
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
 
Automated Screening of Diabetic Retinopathy Using Image Processing
Automated Screening of Diabetic Retinopathy Using Image ProcessingAutomated Screening of Diabetic Retinopathy Using Image Processing
Automated Screening of Diabetic Retinopathy Using Image Processing
 
IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...
IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...
IRJET -An Automatated Learning Approach for Detection of Diabetic Retinopathy...
 
ResNet-n/DR: Automated diagnosis of diabetic retinopathy using a residual neu...
ResNet-n/DR: Automated diagnosis of diabetic retinopathy using a residual neu...ResNet-n/DR: Automated diagnosis of diabetic retinopathy using a residual neu...
ResNet-n/DR: Automated diagnosis of diabetic retinopathy using a residual neu...
 
IRJET- Detection of Diabetic Retinopathy using Convolutional Neural Network
IRJET- 	  Detection of Diabetic Retinopathy using Convolutional Neural NetworkIRJET- 	  Detection of Diabetic Retinopathy using Convolutional Neural Network
IRJET- Detection of Diabetic Retinopathy using Convolutional Neural Network
 
How AI Enhances & Accelerates Diabetic Retinopathy Detection
How AI Enhances & Accelerates Diabetic Retinopathy DetectionHow AI Enhances & Accelerates Diabetic Retinopathy Detection
How AI Enhances & Accelerates Diabetic Retinopathy Detection
 

More from shivubhavv

MANASA FINAL PPT 21.pptxxxxxxxxxxxxxxxxxxx
MANASA FINAL PPT 21.pptxxxxxxxxxxxxxxxxxxxMANASA FINAL PPT 21.pptxxxxxxxxxxxxxxxxxxx
MANASA FINAL PPT 21.pptxxxxxxxxxxxxxxxxxxx
shivubhavv
 
Government polytechnic college-1.pptxabcd
Government polytechnic college-1.pptxabcdGovernment polytechnic college-1.pptxabcd
Government polytechnic college-1.pptxabcd
shivubhavv
 
AICTE PPT slide of Engineering college kr pete
AICTE PPT slide of Engineering college kr peteAICTE PPT slide of Engineering college kr pete
AICTE PPT slide of Engineering college kr pete
shivubhavv
 
pptseminar-16-130305074446-phpapp02.pdff
pptseminar-16-130305074446-phpapp02.pdffpptseminar-16-130305074446-phpapp02.pdff
pptseminar-16-130305074446-phpapp02.pdff
shivubhavv
 
web-scraping-170522083556.pdf.....mmm...
web-scraping-170522083556.pdf.....mmm...web-scraping-170522083556.pdf.....mmm...
web-scraping-170522083556.pdf.....mmm...
shivubhavv
 
Final presentation of diabetic_retinopathy_vascular
Final presentation of diabetic_retinopathy_vascularFinal presentation of diabetic_retinopathy_vascular
Final presentation of diabetic_retinopathy_vascular
shivubhavv
 
Digital Image Processing Module 3 Notess
Digital Image Processing Module 3 NotessDigital Image Processing Module 3 Notess
Digital Image Processing Module 3 Notess
shivubhavv
 

More from shivubhavv (7)

MANASA FINAL PPT 21.pptxxxxxxxxxxxxxxxxxxx
MANASA FINAL PPT 21.pptxxxxxxxxxxxxxxxxxxxMANASA FINAL PPT 21.pptxxxxxxxxxxxxxxxxxxx
MANASA FINAL PPT 21.pptxxxxxxxxxxxxxxxxxxx
 
Government polytechnic college-1.pptxabcd
Government polytechnic college-1.pptxabcdGovernment polytechnic college-1.pptxabcd
Government polytechnic college-1.pptxabcd
 
AICTE PPT slide of Engineering college kr pete
AICTE PPT slide of Engineering college kr peteAICTE PPT slide of Engineering college kr pete
AICTE PPT slide of Engineering college kr pete
 
pptseminar-16-130305074446-phpapp02.pdff
pptseminar-16-130305074446-phpapp02.pdffpptseminar-16-130305074446-phpapp02.pdff
pptseminar-16-130305074446-phpapp02.pdff
 
web-scraping-170522083556.pdf.....mmm...
web-scraping-170522083556.pdf.....mmm...web-scraping-170522083556.pdf.....mmm...
web-scraping-170522083556.pdf.....mmm...
 
Final presentation of diabetic_retinopathy_vascular
Final presentation of diabetic_retinopathy_vascularFinal presentation of diabetic_retinopathy_vascular
Final presentation of diabetic_retinopathy_vascular
 
Digital Image Processing Module 3 Notess
Digital Image Processing Module 3 NotessDigital Image Processing Module 3 Notess
Digital Image Processing Module 3 Notess
 

Recently uploaded

Alluxio Webinar | 10x Faster Trino Queries on Your Data Platform
Alluxio Webinar | 10x Faster Trino Queries on Your Data PlatformAlluxio Webinar | 10x Faster Trino Queries on Your Data Platform
Alluxio Webinar | 10x Faster Trino Queries on Your Data Platform
Alluxio, Inc.
 
Boost Your Savings with These Money Management Apps
Boost Your Savings with These Money Management AppsBoost Your Savings with These Money Management Apps
Boost Your Savings with These Money Management Apps
Jhone kinadey
 
WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
Luigi Fugaro
 
Upturn India Technologies - Web development company in Nashik
Upturn India Technologies - Web development company in NashikUpturn India Technologies - Web development company in Nashik
Upturn India Technologies - Web development company in Nashik
Upturn India Technologies
 
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
kgyxske
 
Going AOT: Everything you need to know about GraalVM for Java applications
Going AOT: Everything you need to know about GraalVM for Java applicationsGoing AOT: Everything you need to know about GraalVM for Java applications
Going AOT: Everything you need to know about GraalVM for Java applications
Alina Yurenko
 
Beginner's Guide to Observability@Devoxx PL 2024
Beginner's  Guide to Observability@Devoxx PL 2024Beginner's  Guide to Observability@Devoxx PL 2024
Beginner's Guide to Observability@Devoxx PL 2024
michniczscribd
 
Migration From CH 1.0 to CH 2.0 and Mule 4.6 & Java 17 Upgrade.pptx
Migration From CH 1.0 to CH 2.0 and  Mule 4.6 & Java 17 Upgrade.pptxMigration From CH 1.0 to CH 2.0 and  Mule 4.6 & Java 17 Upgrade.pptx
Migration From CH 1.0 to CH 2.0 and Mule 4.6 & Java 17 Upgrade.pptx
ervikas4
 
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSISDECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
Tier1 app
 
Why Apache Kafka Clusters Are Like Galaxies (And Other Cosmic Kafka Quandarie...
Why Apache Kafka Clusters Are Like Galaxies (And Other Cosmic Kafka Quandarie...Why Apache Kafka Clusters Are Like Galaxies (And Other Cosmic Kafka Quandarie...
Why Apache Kafka Clusters Are Like Galaxies (And Other Cosmic Kafka Quandarie...
Paul Brebner
 
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
XfilesPro
 
All you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVMAll you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVM
Alina Yurenko
 
The Role of DevOps in Digital Transformation.pdf
The Role of DevOps in Digital Transformation.pdfThe Role of DevOps in Digital Transformation.pdf
The Role of DevOps in Digital Transformation.pdf
mohitd6
 
Orca: Nocode Graphical Editor for Container Orchestration
Orca: Nocode Graphical Editor for Container OrchestrationOrca: Nocode Graphical Editor for Container Orchestration
Orca: Nocode Graphical Editor for Container Orchestration
Pedro J. Molina
 
Mobile App Development Company In Noida | Drona Infotech
Mobile App Development Company In Noida | Drona InfotechMobile App Development Company In Noida | Drona Infotech
Mobile App Development Company In Noida | Drona Infotech
Drona Infotech
 
A Comprehensive Guide on Implementing Real-World Mobile Testing Strategies fo...
A Comprehensive Guide on Implementing Real-World Mobile Testing Strategies fo...A Comprehensive Guide on Implementing Real-World Mobile Testing Strategies fo...
A Comprehensive Guide on Implementing Real-World Mobile Testing Strategies fo...
kalichargn70th171
 
Assure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyesAssure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
如何办理(hull学位证书)英国赫尔大学毕业证硕士文凭原版一模一样
如何办理(hull学位证书)英国赫尔大学毕业证硕士文凭原版一模一样如何办理(hull学位证书)英国赫尔大学毕业证硕士文凭原版一模一样
如何办理(hull学位证书)英国赫尔大学毕业证硕士文凭原版一模一样
gapen1
 
Modelling Up - DDDEurope 2024 - Amsterdam
Modelling Up - DDDEurope 2024 - AmsterdamModelling Up - DDDEurope 2024 - Amsterdam
Modelling Up - DDDEurope 2024 - Amsterdam
Alberto Brandolini
 

Recently uploaded (20)

Alluxio Webinar | 10x Faster Trino Queries on Your Data Platform
Alluxio Webinar | 10x Faster Trino Queries on Your Data PlatformAlluxio Webinar | 10x Faster Trino Queries on Your Data Platform
Alluxio Webinar | 10x Faster Trino Queries on Your Data Platform
 
Boost Your Savings with These Money Management Apps
Boost Your Savings with These Money Management AppsBoost Your Savings with These Money Management Apps
Boost Your Savings with These Money Management Apps
 
WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
WMF 2024 - Unlocking the Future of Data Powering Next-Gen AI with Vector Data...
 
Upturn India Technologies - Web development company in Nashik
Upturn India Technologies - Web development company in NashikUpturn India Technologies - Web development company in Nashik
Upturn India Technologies - Web development company in Nashik
 
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
一比一原版(sdsu毕业证书)圣地亚哥州立大学毕业证如何办理
 
Going AOT: Everything you need to know about GraalVM for Java applications
Going AOT: Everything you need to know about GraalVM for Java applicationsGoing AOT: Everything you need to know about GraalVM for Java applications
Going AOT: Everything you need to know about GraalVM for Java applications
 
Beginner's Guide to Observability@Devoxx PL 2024
Beginner's  Guide to Observability@Devoxx PL 2024Beginner's  Guide to Observability@Devoxx PL 2024
Beginner's Guide to Observability@Devoxx PL 2024
 
Migration From CH 1.0 to CH 2.0 and Mule 4.6 & Java 17 Upgrade.pptx
Migration From CH 1.0 to CH 2.0 and  Mule 4.6 & Java 17 Upgrade.pptxMigration From CH 1.0 to CH 2.0 and  Mule 4.6 & Java 17 Upgrade.pptx
Migration From CH 1.0 to CH 2.0 and Mule 4.6 & Java 17 Upgrade.pptx
 
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSISDECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
DECODING JAVA THREAD DUMPS: MASTER THE ART OF ANALYSIS
 
Why Apache Kafka Clusters Are Like Galaxies (And Other Cosmic Kafka Quandarie...
Why Apache Kafka Clusters Are Like Galaxies (And Other Cosmic Kafka Quandarie...Why Apache Kafka Clusters Are Like Galaxies (And Other Cosmic Kafka Quandarie...
Why Apache Kafka Clusters Are Like Galaxies (And Other Cosmic Kafka Quandarie...
 
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
Everything You Need to Know About X-Sign: The eSign Functionality of XfilesPr...
 
bgiolcb
bgiolcbbgiolcb
bgiolcb
 
All you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVMAll you need to know about Spring Boot and GraalVM
All you need to know about Spring Boot and GraalVM
 
The Role of DevOps in Digital Transformation.pdf
The Role of DevOps in Digital Transformation.pdfThe Role of DevOps in Digital Transformation.pdf
The Role of DevOps in Digital Transformation.pdf
 
Orca: Nocode Graphical Editor for Container Orchestration
Orca: Nocode Graphical Editor for Container OrchestrationOrca: Nocode Graphical Editor for Container Orchestration
Orca: Nocode Graphical Editor for Container Orchestration
 
Mobile App Development Company In Noida | Drona Infotech
Mobile App Development Company In Noida | Drona InfotechMobile App Development Company In Noida | Drona Infotech
Mobile App Development Company In Noida | Drona Infotech
 
A Comprehensive Guide on Implementing Real-World Mobile Testing Strategies fo...
A Comprehensive Guide on Implementing Real-World Mobile Testing Strategies fo...A Comprehensive Guide on Implementing Real-World Mobile Testing Strategies fo...
A Comprehensive Guide on Implementing Real-World Mobile Testing Strategies fo...
 
Assure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyesAssure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyes
 
如何办理(hull学位证书)英国赫尔大学毕业证硕士文凭原版一模一样
如何办理(hull学位证书)英国赫尔大学毕业证硕士文凭原版一模一样如何办理(hull学位证书)英国赫尔大学毕业证硕士文凭原版一模一样
如何办理(hull学位证书)英国赫尔大学毕业证硕士文凭原版一模一样
 
Modelling Up - DDDEurope 2024 - Amsterdam
Modelling Up - DDDEurope 2024 - AmsterdamModelling Up - DDDEurope 2024 - Amsterdam
Modelling Up - DDDEurope 2024 - Amsterdam
 

Diabetic_retinopathy_vascular disease synopsis

  • 1. || JAI SRI GURUDEV || SRI ADICHUNCHANAGIRI SHIKSHANA TRUST ® SJB INSTITUTE OF TECHNOLOGY BGS HEALTH & EDUCATION CITY, KENGERI, BENGALURU-560060 DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING Under the Guidance of Mrs Rajatha Associate Professor Dept. of CSE Presented By: Manasa M [1JB21CS414] Punith HN [1JB21CS419] Rahul V Sanka [1JB21CS420] Sarath Kumar V [1JB21CS422] Project Work Phase – I Presentation On “Severity detection of Diabetic retinopathy Using Deep Learning Algorithms” Severity detection of Diabetic retinopathy using ML 1
  • 2. AGENDA CONTENTS 1. Abstract 2. Introduction 3. Literature Survey 4. Problem Statement 5. Challenges 6. Motivation 7. Objectives 8. Design and Architecture 9. Methodology 10.Implementation 11.Conclusion 12.References Severity detection of Diabetic retinopathy using ML 1
  • 3. ABSTRACT There are several deep learning techniques that are used to perform the predictive analytics over big data in various medical tasks. Predictive analytics in medical healthcare is a challenging task yet ultimately helping the practitioners handle big data-informed timely decisions about patient’s medical health and treatment. This project discusses the predictive analytics in healthcare. Patient’s medical record is obtained for experimental research. The two architectures of deep learning are implemented. Performance and accuracy of these applied algorithms are implemented and compared. Different deep learning techniques used in this research that reveals which algorithm is best suited for the prediction of diabetes over the patient. This project aims to help doctors and practitioners in early stage to predict diabetic retinopathy using deep learning techniques. Severity detection of Diabetic retinopathy using ML 2
  • 4.  Healthcare industry is a very large and sensitive meta data and must be carefully handled. One of the growing extremely fatal diseases all over the world is Diabetes Mellitus.  Some of the useful deep learning techniques for examining the data from diverse perspectives and synopsizing it into valuable information. The accessibility and availability of huge amounts of data are able to provide us useful knowledge unless certain data mining techniques are applied to it.  The Deep Learning consists of an algorithm called Convolutional Neural Network(ConvNet/CNN) which gets the input image, assign importance to various aspects/objects in that image and be able to distinguish one from the other. INTRODUCTION Severity detection of Diabetic retinopathy using ML 3
  • 5. Severity detection of Diabetic retinopathy using ML
  • 6.  Mild nonproliferative diabetic retinopathy: This is the earliest stage of diabetic retinopathy, characterized by tiny areas of swelling in the blood vessels of the retina. These areas of swelling are known as micro aneurysms. Small amounts of fluid can leak into the retina at this stage, triggering swelling of the macula. This is an area near the center of the retina.  Moderate nonproliferative diabetic retinopathy: Increased swelling of tiny blood vessels starts Severity detection of Diabetic retinopathy using ML 5
  • 7. Severity detection of Diabetic retinopathy using ML 7
  • 8. Severity detection of Diabetic retinopathy using ML 6
  • 9. Authors Year of publication Title of the paper Methodology Limitations Balla Goutam Mohammad Farukh Hashmi (Senior Member,Ieee), Zong WooGeem , (Senior Member, Ieee), and Neeraj DhanrajBokde 2022 A Comprehensive Review of Deep Learning Strategies in Retinal Disease Diagnosis Using Fundus Images The proposed review focuses mainly on providing in depth review of various DL strategies recently implemented for retinal disease diagnosis using fundus images. This study also intends to outline possible future directions for new researchers interested in AI-based retinal disease diagnosis. The models trained on IDRID , Messidor, DRIVE datasets may not perform well on other datasets. These may not be suitable for efficient model training, JingWang, Liu Yang, Zhanqian Huo, Weifeng He, and Junwei Luo 2020 Multi-Label Classification of Fundus Images With EfficientNet. The purpose of this study is to establish a framework for automatic identification of multilabel fundus diseases, and to achieve it by designing a corresponding ensemble model. The amount of data for some diseases is very limited, which makes it very difficult to improve the performance of a network. Another basic limitation comes from the black box of the nature of deep networks. The network automatically learns features from images, but the specific features learned are unknown. LITERATURE SURVEY Severity detection of Diabetic retinopathy using ML 9
  • 10. Ayesha Kazi, Prerna Sukhija, Miloy Ajmera, Kailas Devadkar 2021 Processing Retinal Images to Discover Diseases This paper aims to not only accurately classify the disease into one of the three possible abnormalities or assert that it is a healthy retina. The image may fall into more than one category. For example, a retina which shows any presence of Diabetic Retinopathy could also show hints of Glaucoma It cannot determine the presence of a variation in the image (like highlighting, tessellation etc) preceding the classification step, for training the neural network, and to use unique combinations for different cases. Juan Carrillo , Lola Bautista, Jorge Villamizar, Juan Rueda, Mary Sanchez and Daniela Rueda 2021 Glaucoma Detection Using Fundus Images of The Eye This work presents a computational tool for automatic glaucoma detection from fundus images of the eye. This work propose a novel method for cup segmentation, which shows an improvement in the accuracy compared to other methods The vessels segmentation requires an improvement due to some fails in different images and residual noise after the segmentation. Severity detection of Diabetic retinopathy using ML 10
  • 11. PROBLEM STATEMENT The problem addressed in this study is the need for a cost-effective and scalable solution for the detection of diabetic retinopathy (DR), a leading cause of blindness in adults with diabetes. Current methods for DR detection are time-consuming, expensive, and require specialized equipment and trained personnel, making them inaccessible in many regions. The objective of this study is to develop and evaluate a deep learning model for automated DR detection from retinal images, which can improve the accessibility and affordability of DR screening and diagnosis Severity detection of Diabetic retinopathy using ML 8
  • 12. CHALLENGES Severity detection of Diabetic retinopathy using ML 12 Designing a severity detection system for diabetic retinopathy using AI and machine learning involves several challenges. Here are some of the common challenges faced in this domain: 1. Limited and Imbalanced Data: - Insufficient and imbalanced datasets can hinder the training of effective models. Diabetic retinopathy severity levels may not be evenly distributed, leading to biases in the model. 2. Annotation Variability: - Annotating the severity levels of diabetic retinopathy can be subjective, and different experts may provide varying annotations. Achieving a consensus among annotators and ensuring a standardized dataset is challenging. 3. Interpretability and Explain ability: - AI models, particularly deep learning models, are often considered black boxes. It's crucial to interpret and explain the decisions made by the model, especially in medical applications where transparency is essential for gaining trust from healthcare professionals. 4. Generalization Across Diverse Populations: - Models trained on data from a specific population may not generalize well to other populations with different demographics, ethnicities, or healthcare practices. Robustness and generalizability across diverse patient groups are critical considerations.
  • 13. Severity detection of Diabetic retinopathy using ML 13 5. Integration with Clinical Workflow - Integrating AI systems into the existing clinical workflow can be challenging. Ensuring that the severity detection system seamlessly fits into the diagnostic process and complements the workflow of healthcare professionals is crucial for successful implementation. 6. Ethical and Legal Considerations - Handling patient data raises ethical concerns, and there are legal and privacy considerations when working with medical information. Compliance with data protection regulations and the establishment of secure systems are essential. 7. Real-time Processing - In clinical settings, real-time processing is often required. Designing models that can provide timely and accurate predictions is challenging, especially when dealing with high-resolution medical images. 8. Robustness to Image Quality - Medical images can vary in quality due to factors such as equipment differences, variations in lighting conditions, and patient characteristics. Ensuring that the model is robust to variations in image quality is essential for reliable predictions. 9. Continuous Learning and Adaptability - Healthcare data is dynamic, and patterns may change over time. Designing models that can adapt to new data and continuously learn from evolving patterns in diabetic retinopathy is a significant challenge.
  • 14. Severity detection of Diabetic retinopathy using ML 14 MOTIVATION The motivation behind developing a deep learning model for diabetic retinopathy detection is the significant burden of this disease on patients, healthcare systems, and society. Early detection and treatment of DR are critical to preventing blindness and improving patient outcomes. However, current methods for DR detection are expensive and inaccessible in many regions, leading to delays in diagnosis and treatment. By developing a cost-effective and scalable solution for DR detection using deep learning, this study aims to improve the accessibility and affordability of DR screening and diagnosis, ultimately improving patient outcomes and reducing the burden on healthcare systems.
  • 15. OBJECTIVES 1.To develop a deep learning model for automated diabetic retinopathy (DR) detection from retinal images. 2. To compare the performance of the deep learning model with other state-of-the-art DR detection methods to assess its superiority and effectiveness. 3. To assess the clinical implications of the developed deep learning model, including early detection and treatment of DR, reducing the workload of ophthalmologists, and improving patient outcomes. 4. To identify any limitations or challenges faced in the development and evaluation of the deep learning model, such as limited sample size or biased data, that may affect the generalizability of the model. 5. To provide recommendations for future research in the field of DR detection using deep learning, such as the implementation and validation of the model in real-world clinical settings. Severity detection of Diabetic retinopathy using ML 7
  • 16. DESIGN AND ARCHITECTURE A system architecture for diabetic retinopathy detection using deep learning may involve several components, including:  1. Image acquisition: A retinal camera or imaging device is used to acquire high-quality retinal images of patients.  2. Preprocessing: Image preprocessing techniques such as noise reduction, contrast adjustment, and image enhancement are applied to the retinal images to improve image quality.  3. Feature extraction: Deep learning algorithms are used to extract relevant features from the preprocessed images. Severity detection of Diabetic retinopathy using ML 16
  • 17.  4. Training and validation: A deep learning model is trained on a large dataset of retinal images with known diabetic retinopathy labels. The model is validated on a separate dataset to assess its performance.  5. Testing and evaluation: The trained model is tested on new retinal images to assess its diagnostic accuracy and performance.  6. User interface: A user-friendly interface is developed to enable healthcare professionals to interact with the system and input patient information.  7. Patient database: A patient database is maintained to store patient information and retinal images for future reference. Severity detection of Diabetic retinopathy using ML 17
  • 18.  8. Reporting: A reporting module is developed to generate reports summarizing the results of diabetic retinopathy detection and classification for each patient.  9. Integration with EHRs: The system is integrated with electronic health records (EHRs) to facilitate patient care and management.  10. System maintenance and updates: The system is designed for easy maintenance and updates to ensure optimal performance and accuracy over time. Severity detection of Diabetic retinopathy using ML 18
  • 19. Convolutional Neural Networks  A CNN is type of a DNN consists of multiple hidden layers such as convolutional layer, RELU layer, Pooling layer and fully connected a normalized layer.  CNN shares weights in the convolutional layer reducing the memory footprint and increases the performance of the network.  The important features of CNN lie with the 3D volumes of neurons, local connectivity and shared weights.  A feature map is produced by convolution layer through convolution of different sub regions of the input image with a learned kernel. Then, anon- linear activation function is applied through ReLu layer to improve the convergence properties when the error is low. Severity detection of Diabetic retinopathy using ML 19
  • 20.  In pooling layer, a region of the image/feature map is chosen and the pixel with maximum value among them or average values is chosen as the representative pixel so that a 2x2 or 3x3 grid will be reduced to a single scalar value. This results a large reduction in the sample size. Sometimes, the traditional Fully-Connected (FC) layer will be used in conjunction with the convolutional layers toward the output stage Severity detection of Diabetic retinopathy using ML 20
  • 21.  A CNN is composed of several kinds of layers:  Convolutional layer: Creates a feature map to predict the class probabilities for each feature by applying a filter that scans the whole image, few pixels at a time.  Pooling layer (down-sampling): scales down the amount of information the convolutional layer generated for each feature and maintains the most essential information.  Fully connected input layer: flattens the outputs generated by previous layers to turn them into a single vector that can be used as an input for the next layer.  Fully connected layer: Applies weights over the input generated by the feature analysis to predict an accurate label. Severity detection of Diabetic retinopathy using ML 21
  • 22. Severity detection of Diabetic retinopathy using ML 22 Convolutional Neural Network General Architecture
  • 23. DATA FLOW DIAGRAM Severity detection of Diabetic retinopathy using ML 23
  • 24. METHODOLOGY Severity detection of Diabetic retinopathy using ML 14
  • 25. Detecting Diabetic Retinopathy:  Diabetic retinopathy can be detected by using the Retina of the eyes. The eyes having the retina, inside the retina lots of blood vessels are present.  The retina of diabetic patients is different from the normal patient. The blood vessels are chocked inside the retina that indicate the patient has a diabetic.  By using cnn we have detected the leaking blood vessels.  By using pixels images are classified into the part of color sheds. If the blood vessels anywhere choked or leaked then that classified image easily detected the changes into the image.  Then the algorithm detects if the patient has Diabetic Retinopathy or not. Severity detection of Diabetic retinopathy using ML 15
  • 26. IMPLEMENTATION Steps for Implementation  Front-End Development Using Python Flask: Modern computer applications are user-friendly. User interaction is not restricted to console- based I/O. They have a more ergonomic graphical user interface (GUI) thanks to high-speed processors and powerful graphics hardware. These applications can receive inputs through mouse clicks and can enable the user to choose from alternatives with the help of radio buttons, dropdown lists, and other GUI elements. Severity detection of Diabetic retinopathy using ML 26
  • 27.  Flask Programming:  Flask is the standard GUI library for Python. Python when combined with Flask provides a fast and easy way to create GUI applications. Flask provides a powerful object- oriented interface to the Tk GUI toolkit. Flask has several strengths.  It’s cross- platform, so the same code works on Windows, macOS, and Linux. Visual elements are rendered using native operating system elements, so applications built with Flask look like they belong on the platform where they’re run. Severity detection of Diabetic retinopathy using ML 27  The goals of implementation are as follows. Minimize the memory required. Maximize output readability. Maximize source text readability. Minimize the number of source statements. Minimize development time
  • 28. Severity detection of Diabetic retinopathy using ML 28 Conversion from RGB to grayscale
  • 29.  Advantages of converting RGB color space to gray  To store a single-color pixel of an RGB color image we will need 8*3 = 24 bits (8 bit for each color component).  Only 8 bit is required to store a single pixel of the image. So we will need 33 % less memory to store grayscale image than to store an RGB image.  Grayscale images are much easier to work within a variety of task like In many morphological operation and image segmentation problem, it is easier to work with single layered image (Grayscale image) than a three-layered image (RGB color image).  It is also easier to distinguish features of an image when we deal with a single layered image Severity detection of Diabetic retinopathy using ML 29
  • 30. CONCLUSION  Diabetic retinopathy is a leading cause of blindness in diabetic patients, and early detection and treatment are crucial for preventing vision loss. Deep learning algorithms have shown great potential in detecting and classifying diabetic retinopathy from retinal images, which can aid in the early diagnosis and management of the disease. The proposed system for diabetic retinopathy detection using deep learning has the potential to provide accurate and timely diagnoses, which can improve patient outcomes and reduce healthcare costs. While there are still challenges to be addressed, such as the need for large and diverse datasets and interpretability of deep learning models, the advancements in this field continue to offer promise for improving diabetic retinopathy detection and treatment. Severity detection of Diabetic retinopathy using ML 28
  • 31. REFERENCE  1. Abràmoff, M. D., Lou, Y., Erginay, A., Clarida, W., Amelon, R., Folk, J. C., & Niemeijer, M. (2016). Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Investigative Ophthalmology & Visual Science, 57(13), 5200-5206.  2. Bhaskaranand, M., Ramachandra, C., Bhat, S., & Cuadros, J. (2020). Automated diabetic retinopathy screening and monitoring using deep learning. Journal of Healthcare Engineering, 2020, 1-13.  3. Burlina, P. M., Joshi, N., Pekala, M., Pacheco, K. D., Freund, D. E., Bressler, N. M., & Wong, T. Y. (2017). Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA ophthalmology, 135(11), 1170-1176.  4. Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., ... & Webster, D. R. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama, 316(22), 2402-2410.  5. Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C., Liang, H., Baxter, S. L., ... & Keane, P. A. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5), 1122-1131.  6. Li, Z., Keel, S., Liu, C., He, Y., Meng, W., Scheetz, J., ... & Ting, D. S. (2020). An automated grading system for detection of vision-threatening referable diabetic retinopathy on the basis of color fundus photographs. Diabetes care, 43(8), 1748-1755. Severity detection of Diabetic retinopathy using ML 29
  • 32.  7. Osareh, A., Shadgar, B., & Markham, R. (2012). A survey of computer-aided diagnosis of ocular diseases. Computer Methods and Programs in Biomedicine, 108(1), 407-433.  8. Rajalakshmi, R., Subashini, R., Anjana, R. M., Mohan, V., & Deepa, M. (2018). Automated diabetic retinopathy detection in smartphone-based fundus photography using artificial intelligence. Eye, 32(6), 1138-1144.  9. Ramachandra, C., Bhat, S., & Bhaskaranand, M. (2018). Automated grading of diabetic retinopathy using deep neural network. Journal of Healthcare Engineering, 2018, 1-14.  10. Schmidt Erfurth , U., Bogunovic, H., Sadeghipour, A., & Schlegl, T. (2018). Artificial intelligence in retina. Progress in retinal and eye research, 67, 1-29. Severity detection of Diabetic retinopathy using ML 30
  • 33. THANK YOU Severity detection of Diabetic retinopathy using ML 33