Let us first know what is Classification before we talk about how we classify the images and so on. To keep it simple Classification is basically grouping the objects by using the known Label information. So, we need to send Label information along with the data for the model to Classify. In this paper we classify Diabetic Retinopathy images with the help of Deeplearning models which takes images and label as input. We provide Diabetic Retinopathi image with label as input for the model and train it to Classify the Diabetic Retinopathy images. Diabetic Retinopathy (DR), also known as diabetic eye disease, is a medical con-dition in which damage occurs to the retina due to diabetes mellitus.Diabetic Retinopathy (DR) is the leading cause of blindness in the working-age group. 50million Indians sufering from diabetes, the prevalence of those with DR is es-timated between 18percent to 28percent.Regular eye examination among these vulnerable groups is necessary to diagnose DR at an early stage, when it can be treated with the best prognosis. Here we try to classify the DR images at early stages.
Folder | Description |
---|---|
1_Requirements |
Documents detailing requirements and research |
2_Design |
Documents specifying design details |
3_Implementation |
All code and documentation |
4_Test_plan |
Documents with test plans and procedures |
SF No. | Name | Features | Issuess Raised | Issues Resolved | No Test Cases | Test Case Pass |
---|
- Class Imbalance
- less number of samples we overcome by using the image augmentation.
Variable | Bug | Fix |
---|---|---|
input_for Macular Edema | miss classification | model hyper tuning |
input_for Diabetic Retinopathy Grade | miss classification | model hyper tuning |
Integrating both these models into one model for testing
IDRid CANet: Cross-Disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading