4. PROBLEM STATEMENT
๏ถDiabetic retinopathy (DR) is a leading cause of vision-loss
globally.
๏ถOf an estimated 285 million people with diabetes mellitus
worldwide, approximately one third have signs of DR and of
these, a further one third of DR is vision-threatening DR.
๏ถAs it is a leading disease in the west, there needs to be an
solution and way to identify the disease.
5. The overall national rate is 5.4% for the U.S. population age 40 and older, indicating
that nearly 7.7 million older Americans have diabetic retinopathy.
6. APPROACH TO THE PROBLEM
โข Deep Learning: Deep learning is a subset of machine learning in Artificial
Intelligence (AI) that has networks which are capable
from data that is unstructured or unlabeled.
โข Convolution Neural Networks: A neural network is a series of algorithms
attempts to identify underlying relationships in a set of data by using a
process that mimics the way the human brain operates.
โข Tensorflow: TensorFlow is an open source software library for numerical
computation using data flow graphs.
9. HOW ACTUALLY ARE WE DOING IT?
โข We propose a CNN approach to diagnosing DR from digital fundus
images and accurately classifying its severity.
โข We develop a network with CNN architecture and data
which can identify the intricate features involved in the classification
task and consequently provide a diagnosis automatically and
user input.
โข We train this network using a high-end graphics processor unit
on the publicly available Kaggle dataset and demonstrate
results, particularly for a high-level classification task.
10. MODULES
โข Home: It lets the user to see all the functionalities the application provides.
โข Image upload: This screen will ask the user to take a picture of the patientโs
fundus by enabling the camera of the phone.
โข Result: This screen will display the result of the test conducted.
โข Doctorsโ list: This screen will give a list of the doctors that could help the
patient with the treatment of the treatment.
โข Individual doctor: When a particular doctor is selected, all the information
including the location of the clinic and time and contact number will be
provided.
11.
12. REFERENCES
I. โKaggle Diabetic Retinopathy Detection competition reportโ, Ben
Graham, August 6, 2015.
II. Kaggle.com for the dataset of Diabetic Retinopathy.
III. โSeverity Classification of Fundus Images for Diabetic Retinopathyโ,
Jason Su, Stanford Univeristy.
IV. Diagnosing diabetic retinopathy with deep learning, Robert Bogucki,
September 3, 2015.