Project Outline:
Diabetic retinopathy (DR) is a common complication of diabetes that leads to vision loss… One out of two people suffering from diabetes has been diagnosed with some stage of DR. Detection of DR symptoms in time can avert the vision impairment in majority of cases, however such revelation is difficult with present tools and methods.
DR detection is challenging because by the time human readers submit their reviews, often a day or two later, the delayed results lead to lost follow up, miscommunication, and delayed treatment. Clinicians can identify DR by the presence of lesions associated with the vascular abnormalities caused by the disease. While this approach is effective, its resource demands are high. The expertise and equipment required are often lacking in areas where the rate of diabetes in local populations is high and DR detection is most needed.
Early and accurate detection of DR is essential for effective management of the disease and prevention of blindness
The need for a comprehensive and automated method of DR screening has long been recognized, and previous efforts have made good progress using image classification, pattern recognition, and machine learning.
The most common methods used for DR detection are deep learning and machine learning. Deep learning methods such as convolutional neural networks (CNNs) have been used to classify fund
This system takes image processing technique to detect. There are several algorithms proposed on existing, but here for classification, Convolutional Neural Network ( CNN algorithm) is used.The dataset used here is grayscale images with a different 5 categories like No DR, Mild,Moderate,Severe,,Proliferative DR. Analyse and classify these data with Deep network.
Application
Automated detection of diabetic retinopathy has become an active field of research, as it has the potential to reduce the burden of screening in clinical settings.
This review provides an overview of datasets, methods and evaluation metrics used in the development of automated diabetic retinopathy detection systems.
Hardware and Software requirement:
Hardware Requirements: –
- Computer with a processor of 2 GHz or higher
- At least 4 GB of RAM
- Video card with at least 512 MB of RAM
- Display with a minimum resolution of 1024×768
Software Requirements:
- Image processing software such as Python, MATLAB or OpenCV
- Machine learning libraries such as Scikit-learn or TensorFlow
- Deep learning frameworks such as Keras
- Databases MySQL
- Operating system Windows
What you will learn?
- Will have a comprehensive understanding of the datasets, methods and evaluation metrics.
- Identify the challenges and limitations of existing datasets and methods, and analyze the state-of-the-art performance of automated diabetic retinopathy detection systems.
- How to Build an neural network model by training the dataset.
- Design a user interface for providing user input and display the result.
- Plot Confusion matrix for different classes
- Displays the performance parameters Accuracy, Precision, sensitivity and specificity respectively.
