Detection of diabetic retinopathy detection using deep learning on fundus images
Diabetic Retinopathy (DR) is an eye disease caused by diabetic Mellitus (DM).The disease affects mild tissues and blood vessels that can lead to loss of vision. According to statistics, 80% of visually impaired and blind people suffered from long diabetic period of 15 to 20 years. This has become th
Project Title
Detection of diabetic retinopathy detection using deep learning on fundus images
Project Area of Specialization
Project Summary
Diabetic Retinopathy (DR) is an eye disease caused by diabetic Mellitus (DM).The disease affects mild tissues and blood vessels that can lead to loss of vision. According to statistics, 80% of visually impaired and blind people suffered from long diabetic period of 15 to 20 years. This has become the hazardous threat to the health of people. Manual diagnosis of the disease is possible to overcome DR, but at the same time it is overwhelming and tedious and therefore requires an innovative method. Advances in the field of computer science, especially in the field of artificial intelligence, have made detection even easier.
To facilitate the diagnosis process, we develop a deep learning system called DeepDR that can detect the early to late stages of diabetic retinopathy. In this project, Stage detection of diabetic retinopathy from fundus images using a deep learning approach is proposed. The main goal of the project is to detect diabetic retinopathy to stop blindness before it's too late. A prototype of computer aided diagnosis system for diabetic retinopathy detection will be implemented using deep learning. By classifying the images of the patient's retina into five labels numbered from 0 to 4, each label can be "normal," "mild," "moderate," "severe," or "multiple." It will be labeled. Of these five levels, one level is observed as the output label for a particular input fundus image. The proposed system will be implemented using python on Raspberry Pi controller.
Project Objectives
The main objectives of the project are:
- To develop an automatic diabetic retinopathy detection system that analyses fundus images to classify them to assigned severity of the disease.
- To test and validate the classified images which help to diagnose the retinopathic conditions.
- To implement a Computer aided diagnosis system for Diabetic Retinpathy
- To deploy the system in primary health centers
- To make a system that doesn’t require any special skill set to operate.
Project Implementation Method
Diabetic retinopathy is a complication of retina of eyes that can lead to loss of vision and other vision related complications if not treated properly. Early detection of diabetic retinopathy is critical in proper treatment and preventing loss of vision. Deep learning based methods are effective in diabetic retinopathy detection, due to their optimal feature extraction and classification characteristics. There are many image processing techniques for identifying DRs based on domain features such as CDR ratios, textures, and intensity-based features. In the proposed study, texture features are extracted and categorized to perceive the disease. A prototype of computer aided diagnosis system for diabetic retinopathy detection will be implemented using deep learning. The proposed model will be implemented using python on raspberi pi controller.
Benefits of the Project
This project will provide assistance for Ophthalmologist regarding diagnosis of DR and a biomedical system for mass screening of DR.
Technical Details of Final Deliverable
- A Computer aided diagnosis system for Diabetic Retinpathy
- Detection of severity of the disease from early to late stages of diabetic retinopathy using integrated system
Final Deliverable of the Project
Core Industry
Other Industries
Core Technology
Other Technologies
Sustainable Development Goals
Required Resources
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Raspberrry Pie 400 controller | Equipment | 1 | 37200 | 37200 |
| 16gb DDR4 2666Mhz Ram. | Equipment | 1 | 16919 | 16919 |
| Transcend 1TB StoreJet 25M3S USB 3.1 External Hard Drive | Equipment | 1 | 9599 | 9599 |
| Printing Cost | Miscellaneous | 1 | 4000 | 4000 |
| stationary | Miscellaneous | 1 | 1000 | 1000 |
| overheads | Miscellaneous | 1 | 3000 | 3000 |
| Total in (Rs) | 71718 |
If you need this project, please contact me on contact@adikhanofficial.com
Sign Link
style="display:inline;">I affirm that all information submitted through this FYP applicati...
Real Time Collision Detection & Warning System Based on IoT
The most common mean of transportation is a vehicle. Fog is a natural weather phenomenon t...
Modeling PV based DC Micro Grid and to improve the stability margins w...
With declining fossil fuel reserves and unfavourable economic trends, there has been an in...
Smart Solar Power Bench
Regular benches that you see in your park are dull and static, and parks are not utilized...
Design and Development of solar based MPPT Inverter
In our Project we design a buck Boost solar based inverter which buck and boost the v...